2024 |
Liesbet De Vos Jens Nevens, Paul Van Eecke ; Beuls, Katrien Construction grammar and procedural semantics for human-interpretable grounded language processing Journal Article Linguistics Vanguard, (0), 2024. Abstract | BibTeX | Tags: Computational Construction Grammar, Fluid Construction Grammar, grounded language understanding, procedural semantics @article{de2024construction, title = {Construction grammar and procedural semantics for human-interpretable grounded language processing}, author = {Liesbet De Vos, Jens Nevens, Paul Van Eecke and Katrien Beuls}, year = {2024}, date = {2024-03-15}, journal = {Linguistics Vanguard}, number = {0}, abstract = {Groundedlanguageprocessingisacrucialcomponentinmanyartificialintelligencesystems,asitallows agents to communicate about their physical surroundings. State-of-the-art approaches typically employ deep learning techniques that perform end-to-end mappings between natural language expressions and representations grounded in the environment. Although these techniques achieve high levels of accuracy, they are often criticized for their lack of interpretability and their reliance on large amounts of training data. As an alternative, we propose a fully interpretable, data-efficient architecture for grounded language processing. The architecture is based on two main components. The first component comprises an inventory of human-interpretable concepts learned through task-based communicative interactions. These concepts connect the sensorimotor experiences of an agent to meaningful symbols that can be used for reasoning operations. The second component is a computational con- struction grammar that maps between natural language expressions and procedural semantic representations. These representations are grounded through their integration with the learned concepts. We validate the archi- tecture using a variation on the CLEVR benchmark, achieving an accuracy of 96 %. Our experiments demonstrate that the integration of a computational construction grammar with an inventory of interpretable grounded con- cepts can effectively achieve human-interpretable grounded language processing in the CLEVR environment.}, keywords = {Computational Construction Grammar, Fluid Construction Grammar, grounded language understanding, procedural semantics}, pubstate = {published}, tppubtype = {article} } Groundedlanguageprocessingisacrucialcomponentinmanyartificialintelligencesystems,asitallows agents to communicate about their physical surroundings. State-of-the-art approaches typically employ deep learning techniques that perform end-to-end mappings between natural language expressions and representations grounded in the environment. Although these techniques achieve high levels of accuracy, they are often criticized for their lack of interpretability and their reliance on large amounts of training data. As an alternative, we propose a fully interpretable, data-efficient architecture for grounded language processing. The architecture is based on two main components. The first component comprises an inventory of human-interpretable concepts learned through task-based communicative interactions. These concepts connect the sensorimotor experiences of an agent to meaningful symbols that can be used for reasoning operations. The second component is a computational con- struction grammar that maps between natural language expressions and procedural semantic representations. These representations are grounded through their integration with the learned concepts. We validate the archi- tecture using a variation on the CLEVR benchmark, achieving an accuracy of 96 %. Our experiments demonstrate that the integration of a computational construction grammar with an inventory of interpretable grounded con- cepts can effectively achieve human-interpretable grounded language processing in the CLEVR environment. |
Beuls, Katrien; Van Eecke, Paul Construction Grammar and Artificial Intelligence Book Chapter Forthcoming Fried, Mirjam; Nikiforidou, Kiki (Ed.): The Cambridge Handbook of Construction Grammar, Cambridge University Press, Cambridge, Forthcoming. Abstract | BibTeX | Tags: Fluid Construction Grammar @inbook{beuls2024construction, title = {Construction Grammar and Artificial Intelligence}, author = {Katrien Beuls and Paul {Van Eecke}}, editor = {Mirjam Fried and Kiki Nikiforidou}, year = {2024}, date = {2024-00-00}, booktitle = {The Cambridge Handbook of Construction Grammar}, publisher = {Cambridge University Press}, address = {Cambridge}, abstract = {In this chapter, we argue that it is highly beneficial for the contemporary construction grammarian to have a thorough understanding of the strong relationship between the research fields of construction grammar and artificial intelligence. We start by unravelling the historical links between the two fields, showing that their relationship is rooted in a common attitude towards human communication and language. We then discuss the first direction of influence, focusing on how insights and techniques from the field of artificial intelligence play an important role in operationalising, validating, and scaling constructionist approaches to language. We then proceed to the second direction of influence, highlighting the relevance of construction grammar insights and analyses to the artificial intelligence endeavour of building truly intelligent agents. We support our case with a variety of illustrative examples and conclude that the further elaboration of this relationship will play a key role in shaping the future of the field of construction grammar.}, keywords = {Fluid Construction Grammar}, pubstate = {forthcoming}, tppubtype = {inbook} } In this chapter, we argue that it is highly beneficial for the contemporary construction grammarian to have a thorough understanding of the strong relationship between the research fields of construction grammar and artificial intelligence. We start by unravelling the historical links between the two fields, showing that their relationship is rooted in a common attitude towards human communication and language. We then discuss the first direction of influence, focusing on how insights and techniques from the field of artificial intelligence play an important role in operationalising, validating, and scaling constructionist approaches to language. We then proceed to the second direction of influence, highlighting the relevance of construction grammar insights and analyses to the artificial intelligence endeavour of building truly intelligent agents. We support our case with a variety of illustrative examples and conclude that the further elaboration of this relationship will play a key role in shaping the future of the field of construction grammar. |
2023 |
Doumen, Jonas; Beuls, Katrien; Van Eecke, Paul Modelling Language Acquisition through Syntactico-Semantic Pattern Finding Inproceedings Findings of the Association for Computational Linguistics: EACL 2023, pp. 1317-1327, Association for Computational Linguistics, 2023. Abstract | Links | BibTeX | Tags: Fluid Construction Grammar @inproceedings{doumen2023modelling, title = {Modelling Language Acquisition through Syntactico-Semantic Pattern Finding}, author = {Jonas Doumen and Katrien Beuls and Paul {Van Eecke}}, url = {https://aclanthology.org/2023.findings-eacl.99/}, year = {2023}, date = {2023-05-01}, booktitle = {Findings of the Association for Computational Linguistics: EACL 2023}, pages = {1317-1327}, publisher = {Association for Computational Linguistics}, abstract = {Usage-based theories of language acquisition have extensively documented the processes by which children acquire language through communicative interaction. Notably, Tomasello (2003) distinguishes two main cognitive capacities that underlie human language acquisition: intention reading and pattern finding. Intention reading is the process by which children try to continuously reconstruct the intended meaning of their interlocutors. Pattern finding refers to the process that allows them to distil linguistic schemata from multiple communicative interactions. Even though the fields of cognitive science and psycholinguistics have studied these processes in depth, no faithful computational operationalisations of these mechanisms through which children learn language exist to date. The research on which we report in this paper aims to fill part of this void by introducing a computational operationalisation of syntactico-semantic pattern finding. Concretely, we present a methodology for learning grammars based on similarities and differences in the form and meaning of linguistic observations alone. Our methodology is able to learn compositional lexical and item-based constructions of variable extent and degree of abstraction, along with a network of emergent syntactic categories. We evaluate our methodology on the CLEVR benchmark dataset and show that the methodology allows for fast, incremental and effective learning. The constructions and categorial network that result from the learning process are fully transparent and bidirectional, facilitating both language comprehension and production. Theoretically, our model provides computational evidence for the learnability of usage-based constructionist theories of language acquisition. Practically, the techniques that we present facilitate the learning of computationally tractable, usage-based construction grammars, which are applicable for natural language understanding and production tasks.}, keywords = {Fluid Construction Grammar}, pubstate = {published}, tppubtype = {inproceedings} } Usage-based theories of language acquisition have extensively documented the processes by which children acquire language through communicative interaction. Notably, Tomasello (2003) distinguishes two main cognitive capacities that underlie human language acquisition: intention reading and pattern finding. Intention reading is the process by which children try to continuously reconstruct the intended meaning of their interlocutors. Pattern finding refers to the process that allows them to distil linguistic schemata from multiple communicative interactions. Even though the fields of cognitive science and psycholinguistics have studied these processes in depth, no faithful computational operationalisations of these mechanisms through which children learn language exist to date. The research on which we report in this paper aims to fill part of this void by introducing a computational operationalisation of syntactico-semantic pattern finding. Concretely, we present a methodology for learning grammars based on similarities and differences in the form and meaning of linguistic observations alone. Our methodology is able to learn compositional lexical and item-based constructions of variable extent and degree of abstraction, along with a network of emergent syntactic categories. We evaluate our methodology on the CLEVR benchmark dataset and show that the methodology allows for fast, incremental and effective learning. The constructions and categorial network that result from the learning process are fully transparent and bidirectional, facilitating both language comprehension and production. Theoretically, our model provides computational evidence for the learnability of usage-based constructionist theories of language acquisition. Practically, the techniques that we present facilitate the learning of computationally tractable, usage-based construction grammars, which are applicable for natural language understanding and production tasks. |
Beuls, Katrien; Van Eecke, Paul Fluid Construction Grammar: State of the Art and Future Outlook Inproceedings Proceedings of the First International Workshop on Construction Grammars and NLP (CxGs+NLP, GURT/SyntaxFest 2023), pp. 41-50, 2023. Links | BibTeX | Tags: Fluid Construction Grammar @inproceedings{beuls2023fluid, title = {Fluid Construction Grammar: State of the Art and Future Outlook}, author = {Katrien Beuls and Paul {Van Eecke}}, url = {https://aclanthology.org/2023.cxgsnlp-1.6/}, year = {2023}, date = {2023-03-01}, booktitle = {Proceedings of the First International Workshop on Construction Grammars and NLP (CxGs+NLP, GURT/SyntaxFest 2023)}, pages = {41-50}, keywords = {Fluid Construction Grammar}, pubstate = {published}, tppubtype = {inproceedings} } |
2022 |
Van Eecke, Paul ; Nevens, Jens; Beuls, Katrien Neural Heuristics for Constructional Language Processing Journal Article Journal of Language Modelling, 10 (2), pp. 287–314, 2022. Abstract | Links | BibTeX | Tags: Fluid Construction Grammar @article{vaneecke2022neural, title = {Neural Heuristics for Constructional Language Processing}, author = {Paul {Van Eecke} and Jens Nevens and Katrien Beuls}, url = {https://jlm.ipipan.waw.pl/index.php/JLM/article/view/318}, year = {2022}, date = {2022-12-28}, journal = {Journal of Language Modelling}, volume = {10}, number = {2}, pages = {287–314}, abstract = {Constructionist approaches to language make use of form-meaning pairings, called constructions, to capture all linguistic knowledge that is necessary for comprehending and producing natural language expressions. Language processing consists then in combining the constructions of a grammar in such a way that they solve a given language comprehension or production problem. Finding such an adequate sequence of constructions constitutes a search problem that is combinatorial in nature and becomes intractable as grammars increase in size. In this paper, we introduce a neural methodology for learning heuristics that substantially optimise the search processes involved in constructional language processing. We validate the methodology in a case study for the CLEVR benchmark dataset. We show that our novel methodology outperforms state-of-the-art techniques in terms of size of the search space and time of computation, most markedly in the production direction. The results reported on in this paper have the potential to overcome the major efficiency obstacle that hinders current efforts in learning large-scale construction grammars, thereby contributing to the development of scalable constructional language processing systems.}, keywords = {Fluid Construction Grammar}, pubstate = {published}, tppubtype = {article} } Constructionist approaches to language make use of form-meaning pairings, called constructions, to capture all linguistic knowledge that is necessary for comprehending and producing natural language expressions. Language processing consists then in combining the constructions of a grammar in such a way that they solve a given language comprehension or production problem. Finding such an adequate sequence of constructions constitutes a search problem that is combinatorial in nature and becomes intractable as grammars increase in size. In this paper, we introduce a neural methodology for learning heuristics that substantially optimise the search processes involved in constructional language processing. We validate the methodology in a case study for the CLEVR benchmark dataset. We show that our novel methodology outperforms state-of-the-art techniques in terms of size of the search space and time of computation, most markedly in the production direction. The results reported on in this paper have the potential to overcome the major efficiency obstacle that hinders current efforts in learning large-scale construction grammars, thereby contributing to the development of scalable constructional language processing systems. |
Nevens, Jens; Doumen, Jonas; Van Eecke, Paul ; Beuls, Katrien Language Acquisition through Intention Reading and Pattern Finding Inproceedings Proceedings of the 29th International Conference on Computational Linguistics, pp. 15-25, 2022. Links | BibTeX | Tags: Fluid Construction Grammar @inproceedings{nevens2022language, title = {Language Acquisition through Intention Reading and Pattern Finding}, author = {Jens Nevens and Jonas Doumen and Paul {Van Eecke} and Katrien Beuls}, url = {https://aclanthology.org/2022.coling-1.2/}, year = {2022}, date = {2022-10-01}, booktitle = {Proceedings of the 29th International Conference on Computational Linguistics}, pages = {15-25}, keywords = {Fluid Construction Grammar}, pubstate = {published}, tppubtype = {inproceedings} } |
van Trijp, Remi ; Beuls, Katrien; Van Eecke, Paul The FCG Editor: An innovative environment for engineering computational construction grammars Journal Article PLOS ONE, 17 (6), pp. 1-27, 2022. Abstract | Links | BibTeX | Tags: Computational Construction Grammar, Fluid Construction Grammar @article{vantrijp2022fcg, title = {The FCG Editor: An innovative environment for engineering computational construction grammars}, author = {Remi {van Trijp} and Katrien Beuls and Paul {Van Eecke}}, doi = {10.1371/journal.pone.0269708}, year = {2022}, date = {2022-01-01}, journal = {PLOS ONE}, volume = {17}, number = {6}, pages = {1-27}, publisher = {Public Library of Science}, abstract = {Since its inception in the mid-eighties, the field of construction grammar has been steadily growing and constructionist approaches to language have by now become a mainstream paradigm for linguistic research. While the construction grammar community has traditionally focused on theoretical, experimental and corpus-based research, the importance of computational methodologies is now rapidly increasing. This movement has led to the establishment of a number of exploratory computational construction grammar formalisms, which facilitate the implementation of construction grammars, as well as their use for language processing purposes. Yet, implementing large grammars using these formalisms still remains a challenging task, partly due to a lack of powerful and user-friendly tools for computational construction grammar engineering. In order to overcome this obstacle, this paper introduces the FCG Editor, a dedicated and innovative integrated development environment for the Fluid Construction Grammar formalism. Offering a straightforward installation and a user-friendly, interactive interface, the FCG Editor is an accessible, yet powerful tool for construction grammarians who wish to operationalise their construction grammar insights and analyses in order to computationally verify them, corroborate them with corpus data, or integrate them in language technology applications.}, keywords = {Computational Construction Grammar, Fluid Construction Grammar}, pubstate = {published}, tppubtype = {article} } Since its inception in the mid-eighties, the field of construction grammar has been steadily growing and constructionist approaches to language have by now become a mainstream paradigm for linguistic research. While the construction grammar community has traditionally focused on theoretical, experimental and corpus-based research, the importance of computational methodologies is now rapidly increasing. This movement has led to the establishment of a number of exploratory computational construction grammar formalisms, which facilitate the implementation of construction grammars, as well as their use for language processing purposes. Yet, implementing large grammars using these formalisms still remains a challenging task, partly due to a lack of powerful and user-friendly tools for computational construction grammar engineering. In order to overcome this obstacle, this paper introduces the FCG Editor, a dedicated and innovative integrated development environment for the Fluid Construction Grammar formalism. Offering a straightforward installation and a user-friendly, interactive interface, the FCG Editor is an accessible, yet powerful tool for construction grammarians who wish to operationalise their construction grammar insights and analyses in order to computationally verify them, corroborate them with corpus data, or integrate them in language technology applications. |
2021 |
Beuls, Katrien; Van Eecke, Paul ; Cangalovic, Vanja Sophie A Computational Construction Grammar Approach to Semantic Frame Extraction Journal Article Linguistics Vanguard, 7 (1), pp. 20180015, 2021. Links | BibTeX | Tags: Computational Construction Grammar, Fluid Construction Grammar @article{beuls2021computational, title = {A Computational Construction Grammar Approach to Semantic Frame Extraction}, author = {Katrien Beuls and Paul {Van Eecke} and Vanja Sophie Cangalovic}, url = {https://ehai.ai.vub.ac.be/assets/pdfs/beuls2021computational.pdf}, doi = {https://doi.org/10.1515/lingvan-2018-0015}, year = {2021}, date = {2021-01-01}, journal = {Linguistics Vanguard}, volume = {7}, number = {1}, pages = {20180015}, publisher = {De Gruyter}, keywords = {Computational Construction Grammar, Fluid Construction Grammar}, pubstate = {published}, tppubtype = {article} } |
2020 |
van Trijp, Remi Making good on a promise: Multi-dimensional constructions Journal Article Belgian Journal of Linguistics, 34 , pp. 357-370, 2020, ISBN: 9789027259851. Abstract | Links | BibTeX | Tags: Fluid Construction Grammar @article{vantrijp2020making, title = {Making good on a promise: Multi-dimensional constructions}, author = {Remi van Trijp}, editor = {Timothy Colleman and Frank Brisard and Astrid De Wit and Renata Enghels and Nikos Koutsoukos and Tanja Mortelmans and María Sol Sansiñena}, url = {https://benjamins.com/catalog/bjl.00059.tri}, isbn = {9789027259851}, year = {2020}, date = {2020-01-01}, journal = {Belgian Journal of Linguistics}, volume = {34}, pages = {357-370}, abstract = {Construction Grammar was founded on the promise of maximal empirical coverage without compromising on formal precision. Its main claim is that all linguistic knowledge can be represented as constructions, similar to the notion of constructions from traditional grammars. As such, Construction Grammar may finally reconcile the needs of descriptive and theoretical linguistics by establishing a common ground between them. Unfortunately, while the construction grammar community has developed a sophisticated understanding of what a construction is supposed to be, many critics still believe that a construction is simply a new jacket for traditional linguistic analyses and therefore inherits all of the problems of those analyses. The goal of this article is to refute such criticisms by showing how constructions can be formalized as open-ended and multidimensional linguistic representations that make no prior assumptions about the structure of a language. While this article’s proposal can be simply written down in a pen-and-paper style, it verifies the validity of its approach through a computational implementation of German field topology in Fluid Construction Grammar.}, keywords = {Fluid Construction Grammar}, pubstate = {published}, tppubtype = {article} } Construction Grammar was founded on the promise of maximal empirical coverage without compromising on formal precision. Its main claim is that all linguistic knowledge can be represented as constructions, similar to the notion of constructions from traditional grammars. As such, Construction Grammar may finally reconcile the needs of descriptive and theoretical linguistics by establishing a common ground between them. Unfortunately, while the construction grammar community has developed a sophisticated understanding of what a construction is supposed to be, many critics still believe that a construction is simply a new jacket for traditional linguistic analyses and therefore inherits all of the problems of those analyses. The goal of this article is to refute such criticisms by showing how constructions can be formalized as open-ended and multidimensional linguistic representations that make no prior assumptions about the structure of a language. While this article’s proposal can be simply written down in a pen-and-paper style, it verifies the validity of its approach through a computational implementation of German field topology in Fluid Construction Grammar. |
2018 |
Van Eecke, Paul ; Beuls, Katrien Exploring the Creative Potential of Computational Construction Grammar Journal Article Zeitschrift für Anglistik und Amerikanistik, 66 (3), pp. 341–355, 2018, ISSN: 2196-4726. Abstract | Links | BibTeX | Tags: Computational Construction Grammar, Creativity, Fluid Construction Grammar @article{30da883aaecd4f11814c93a15a89855f, title = {Exploring the Creative Potential of Computational Construction Grammar}, author = {Paul {Van Eecke} and Katrien Beuls}, url = {https://ehai.ai.vub.ac.be/assets/pdfs/fcg-creativity.pdf}, doi = {10.1515/zaa-2018-0029}, issn = {2196-4726}, year = {2018}, date = {2018-01-01}, journal = {Zeitschrift für Anglistik und Amerikanistik}, volume = {66}, number = {3}, pages = {341--355}, publisher = {Walter de Gruyter GmbH}, abstract = {Computational construction grammar aims to provide concrete processing models that operationalise construction grammar accounts of the different aspects of language. This paper discusses the computational mechanisms that allow construction grammar models to exhibit, to a certain extent, the creativity and inventiveness that is observed in human language use. It addresses two main types of language-related creativity. The first type concerns the ‘free combination of constructions,’ which gives rise to the open-endedness of language. The second type concerns the ‘appropriate violation of usual constraints’ that permits language users to go beyond what is possible when adhering to the usual constraints of the language, and be truly creative by relaxing these constraints and by introducing novel constructions. All mechanisms and examples discussed in this paper are fully operationalised and implemented in Fluid Construction Grammar.}, keywords = {Computational Construction Grammar, Creativity, Fluid Construction Grammar}, pubstate = {published}, tppubtype = {article} } Computational construction grammar aims to provide concrete processing models that operationalise construction grammar accounts of the different aspects of language. This paper discusses the computational mechanisms that allow construction grammar models to exhibit, to a certain extent, the creativity and inventiveness that is observed in human language use. It addresses two main types of language-related creativity. The first type concerns the ‘free combination of constructions,’ which gives rise to the open-endedness of language. The second type concerns the ‘appropriate violation of usual constraints’ that permits language users to go beyond what is possible when adhering to the usual constraints of the language, and be truly creative by relaxing these constraints and by introducing novel constructions. All mechanisms and examples discussed in this paper are fully operationalised and implemented in Fluid Construction Grammar. |
2017 |
Steels, Luc Basics of Fluid Construction Grammar Journal Article Constructions and frames, 9 (2), pp. 178-255, 2017, ISBN: 1876-1933. Abstract | Links | BibTeX | Tags: Fluid Construction Grammar @article{Steels2017, title = {Basics of Fluid Construction Grammar}, author = {Luc Steels}, doi = {https://doi.org/10.1075/cf.00002.ste}, isbn = {1876-1933}, year = {2017}, date = {2017-12-30}, journal = {Constructions and frames}, volume = {9}, number = {2}, pages = {178-255}, abstract = {Fluid Construction Grammar (FCG) is a fully operational computational platform for developing grammars from a constructional perspective. It contains mechanisms for representing grammars and for using them in computational experiments and applications in language understanding, production and learning. FCG can be used by grammar writers who want to test whether their grammar fragments are complete and coherent for the domain they are investigating (for example verb phrases) or who are working in a team and have to share grammar fragments with others. It can be used by computational linguists implementing practical language processing systems or exploring how machine learning algorithms can acquire grammars. This paper introduces some of the basic mechanisms of FCG, illustrated with examples.}, keywords = {Fluid Construction Grammar}, pubstate = {published}, tppubtype = {article} } Fluid Construction Grammar (FCG) is a fully operational computational platform for developing grammars from a constructional perspective. It contains mechanisms for representing grammars and for using them in computational experiments and applications in language understanding, production and learning. FCG can be used by grammar writers who want to test whether their grammar fragments are complete and coherent for the domain they are investigating (for example verb phrases) or who are working in a team and have to share grammar fragments with others. It can be used by computational linguists implementing practical language processing systems or exploring how machine learning algorithms can acquire grammars. This paper introduces some of the basic mechanisms of FCG, illustrated with examples. |
Van Eecke, Paul Robust processing of the Dutch verb phrase Journal Article Constructions and Frames, 9 (2), pp. 226–250, 2017, ISSN: 1876-1933. Abstract | Links | BibTeX | Tags: bidirectionality, construction grammar, Dutch verb phrase, Fluid Construction Grammar, language comprehension, language production, robustness @article{2f96ee41e1784dc4980ab03daa5c243d, title = {Robust processing of the Dutch verb phrase}, author = {Paul {Van Eecke}}, doi = {10.1075/cf.00003.van}, issn = {1876-1933}, year = {2017}, date = {2017-01-01}, journal = {Constructions and Frames}, volume = {9}, number = {2}, pages = {226--250}, publisher = {John Benjamins Publishing Company}, abstract = {The Dutch verb phrase (VP) is notorious for its syntactic intricacies. There are three main reasons why it is difficult to robustly handle its complexity in a processing model. First of all, a single VP can contain multiple modal auxiliaries (‘modal stacking’). Second, perfect auxiliaries can not only take a past participle as their argument but also a modal auxiliary in the infinitive form. Finally, there are various word orders in which the verb forms can appear. The first part of this paper presents a fully operational precision processing model of the Dutch VP in Fluid Construction Grammar. The model shows that the aforementioned challenges can be overcome by carefully managing the hierarchical relations between the elements of the VP. The second part introduces a robust comprehension method, which can process VPs containing morphological and word order errors. This method allows in many cases to recover the intended meaning of an erroneous VP, as well as to correct its form, using a strategy that exploits the deep semantic analyses and the bidirectional nature of the model.}, keywords = {bidirectionality, construction grammar, Dutch verb phrase, Fluid Construction Grammar, language comprehension, language production, robustness}, pubstate = {published}, tppubtype = {article} } The Dutch verb phrase (VP) is notorious for its syntactic intricacies. There are three main reasons why it is difficult to robustly handle its complexity in a processing model. First of all, a single VP can contain multiple modal auxiliaries (‘modal stacking’). Second, perfect auxiliaries can not only take a past participle as their argument but also a modal auxiliary in the infinitive form. Finally, there are various word orders in which the verb forms can appear. The first part of this paper presents a fully operational precision processing model of the Dutch VP in Fluid Construction Grammar. The model shows that the aforementioned challenges can be overcome by carefully managing the hierarchical relations between the elements of the VP. The second part introduces a robust comprehension method, which can process VPs containing morphological and word order errors. This method allows in many cases to recover the intended meaning of an erroneous VP, as well as to correct its form, using a strategy that exploits the deep semantic analyses and the bidirectional nature of the model. |
Beuls, Katrien; Steels, Luc Approaches to the verb phrase in Fluid Construction Grammar Journal Article Constructions and Frames, 9 (2), pp. 175-177, 2017, ISSN: 1876-1933. Abstract | BibTeX | Tags: Fluid Construction Grammar @article{7330bce0ab6a46d3ad31ab3152494c2e, title = {Approaches to the verb phrase in Fluid Construction Grammar}, author = {Katrien Beuls and Luc Steels}, issn = {1876-1933}, year = {2017}, date = {2017-01-01}, journal = {Constructions and Frames}, volume = {9}, number = {2}, pages = {175-177}, publisher = {John Benjamins Publishing Company}, abstract = {Despite the growing influence of construction grammar in many different areas of language research, we still lack a widely used computational platform for defining and testing construction grammars and for studying constructional processing in parsing, producing, and learning grammars. Such a platform is needed because otherwise we cannot hope to develop and test construction grammars with wide empirical coverage and we cannot use construction grammars as the core of natural language processing applications. But various groups are currently making significant progress in developing operational platforms. This special issue focuses on one of them, namely Fluid Construction Grammar (FCG). The papers collected here provide, on the one hand, more information about FCG by introducing the basics mechanisms by which constructions are represented and processed and by illustrating how the formalism …}, keywords = {Fluid Construction Grammar}, pubstate = {published}, tppubtype = {article} } Despite the growing influence of construction grammar in many different areas of language research, we still lack a widely used computational platform for defining and testing construction grammars and for studying constructional processing in parsing, producing, and learning grammars. Such a platform is needed because otherwise we cannot hope to develop and test construction grammars with wide empirical coverage and we cannot use construction grammars as the core of natural language processing applications. But various groups are currently making significant progress in developing operational platforms. This special issue focuses on one of them, namely Fluid Construction Grammar (FCG). The papers collected here provide, on the one hand, more information about FCG by introducing the basics mechanisms by which constructions are represented and processed and by illustrating how the formalism … |
Hoorens, Sebastien; Beuls, Katrien; Van Eecke, Paul Constructions at Work! Visualising Linguistic Pathways for Computational Construction Grammar Inproceedings Proceedings of the 29th Benelux Conference on Artificial Intelligence, pp. 224–237, 2017. Abstract | Links | BibTeX | Tags: Fluid Construction Grammar @inproceedings{55c637613d494377a4964f7d70076018, title = {Constructions at Work! Visualising Linguistic Pathways for Computational Construction Grammar}, author = {Sebastien Hoorens and Katrien Beuls and Paul {Van Eecke}}, url = {https://ehai.ai.vub.ac.be/assets/pdfs/hoorens2017constructions.pdf}, year = {2017}, date = {2017-01-01}, booktitle = {Proceedings of the 29th Benelux Conference on Artificial Intelligence}, pages = {224--237}, abstract = {Computational construction grammar combines well known concepts from artificial intelligence, linguistics and computer science into fully operational language processing models. These models allow to map an utterance to its meaning representation (comprehension), as well as to map a meaning representation to an utterance (formulation). The processing machinery is based on the unification of usage-patterns that combine morpho-syntactic and semantic information (constructions) with intermediate structures that contain all information that is known at a certain point in processing (transient structures). Language processing is then implemented as a search process, which searches for a sequence of constructions (a linguistic pathway) that successfully transforms an initial transient structure containing the input into a transient structure that qualifies as a goal. For larger grammars, these linguistic pathways become increasingly more complex, which makes them difficult to interpret and debug for the human researcher. In order to accommodate this problem, we present a novel approach to visualising the outcome of constructional language processing. The linguistic pathways are visualised as graphs featuring the applied constructions, why they could apply, with which bindings, and what information they have added. The visualisation tool is concretely implemented for Fluid Construction Grammar, but is also of interest to other flavours of computational construction grammar, as well as more generally to other unification-based search problems of high complexity.}, keywords = {Fluid Construction Grammar}, pubstate = {published}, tppubtype = {inproceedings} } Computational construction grammar combines well known concepts from artificial intelligence, linguistics and computer science into fully operational language processing models. These models allow to map an utterance to its meaning representation (comprehension), as well as to map a meaning representation to an utterance (formulation). The processing machinery is based on the unification of usage-patterns that combine morpho-syntactic and semantic information (constructions) with intermediate structures that contain all information that is known at a certain point in processing (transient structures). Language processing is then implemented as a search process, which searches for a sequence of constructions (a linguistic pathway) that successfully transforms an initial transient structure containing the input into a transient structure that qualifies as a goal. For larger grammars, these linguistic pathways become increasingly more complex, which makes them difficult to interpret and debug for the human researcher. In order to accommodate this problem, we present a novel approach to visualising the outcome of constructional language processing. The linguistic pathways are visualised as graphs featuring the applied constructions, why they could apply, with which bindings, and what information they have added. The visualisation tool is concretely implemented for Fluid Construction Grammar, but is also of interest to other flavours of computational construction grammar, as well as more generally to other unification-based search problems of high complexity. |
Van Eecke, Paul ; Beuls, Katrien Meta-Layer Problem Solving for Computational Construction Grammar Inproceedings The 2017 AAAI Spring Symposium Series, pp. 258–265, 2017, ISBN: 978-1-57735-754-4. Abstract | Links | BibTeX | Tags: Fluid Construction Grammar @inproceedings{d7b46cb03a7249b59bf572514b95a855, title = {Meta-Layer Problem Solving for Computational Construction Grammar}, author = {Paul {Van Eecke} and Katrien Beuls}, url = {https://ehai.ai.vub.ac.be/assets/pdfs/meta-layer.pdf}, isbn = {978-1-57735-754-4}, year = {2017}, date = {2017-01-01}, booktitle = {The 2017 AAAI Spring Symposium Series}, pages = {258--265}, abstract = {Bearing the word “fluid” in its name, Fluid Construction Grammar (FCG) is known for its open-ended nature when it comes to formalising linguistic knowledge in the form of constructions. Yet, it is also flexible with respect to the processing of input that cannot be handled in the standard way. This paper presents a meta-layer architecture that is fully integrated into the FCG language processing framework, as well as a number of powerful and general operators that can be used within this architecture for on-the-fly problem solving and learning of lexical and grammatical constructions.}, keywords = {Fluid Construction Grammar}, pubstate = {published}, tppubtype = {inproceedings} } Bearing the word “fluid” in its name, Fluid Construction Grammar (FCG) is known for its open-ended nature when it comes to formalising linguistic knowledge in the form of constructions. Yet, it is also flexible with respect to the processing of input that cannot be handled in the standard way. This paper presents a meta-layer architecture that is fully integrated into the FCG language processing framework, as well as a number of powerful and general operators that can be used within this architecture for on-the-fly problem solving and learning of lexical and grammatical constructions. |
Beuls, Katrien; Knight, Yana; Spranger, Michael Russian verbs of motion and their aspectual partners in Fluid Construction Grammar Journal Article Constructions and Frames, 9 (2), pp. 300-318, 2017, ISSN: 1876-1933. Abstract | BibTeX | Tags: Fluid Construction Grammar @article{22e226cfb1d14687a0cd867b8a2f7942, title = {Russian verbs of motion and their aspectual partners in Fluid Construction Grammar}, author = {Katrien Beuls and Yana Knight and Michael Spranger}, issn = {1876-1933}, year = {2017}, date = {2017-01-01}, journal = {Constructions and Frames}, volume = {9}, number = {2}, pages = {300-318}, publisher = {John Benjamins Publishing Company}, abstract = {Russian boasts a highly complex aspectual system which can appear irregular and difficult to learn. It has recently been suggested that motion verbs, which are normally seen as exceptional in their nature, may in fact be at the core of this system, motivating aspectual behavior based on stem directionality. This suggests that analyzing motion verbs may help understand the Russian aspectual system as a whole. The present work demonstrates how Russian motion verbs and their aspectual partners can be implemented and processed successfully with Fluid Constructional Grammar. The study presents an example of language processing in both production and comprehension in operation and highlights the flexibility and power of this formalism, despite the challenges that this complex aspectual system poses.}, keywords = {Fluid Construction Grammar}, pubstate = {published}, tppubtype = {article} } Russian boasts a highly complex aspectual system which can appear irregular and difficult to learn. It has recently been suggested that motion verbs, which are normally seen as exceptional in their nature, may in fact be at the core of this system, motivating aspectual behavior based on stem directionality. This suggests that analyzing motion verbs may help understand the Russian aspectual system as a whole. The present work demonstrates how Russian motion verbs and their aspectual partners can be implemented and processed successfully with Fluid Constructional Grammar. The study presents an example of language processing in both production and comprehension in operation and highlights the flexibility and power of this formalism, despite the challenges that this complex aspectual system poses. |
2016 |
Steels, Luc; Szathmáry, Eörs Fluid construction grammar as a biological system Journal Article Linguistics Vanguard, 2 (1), 2016, ISBN: 2199-174X. Abstract | Links | BibTeX | Tags: Fluid Construction Grammar @article{Steels2016, title = {Fluid construction grammar as a biological system}, author = {Luc Steels and Eörs Szathmáry}, doi = {https://doi.org/10.1515/lingvan-2015-0022}, isbn = {2199-174X}, year = {2016}, date = {2016-12-01}, journal = {Linguistics Vanguard}, volume = {2}, number = {1}, abstract = {Mapping insights and frameworks from one scientific domain to another is often useful because it encourages communication between different scientific fields and acts as a conduit for the exchange of mathematical and computational tools. This paper introduces analogies between concepts and mechanisms from molecular biology and language processing. The main purpose is to find ways for understanding language as a ‘living’, dynamically evolving, self-organizing system. The analogies have been the main source of inspiration for a computational implementation of construction grammar, called Fluid Construction Grammar (FCG). The paper describes briefly the biological analogies underlying FCG and discusses the opportunities for further research that these analogies open up.}, keywords = {Fluid Construction Grammar}, pubstate = {published}, tppubtype = {article} } Mapping insights and frameworks from one scientific domain to another is often useful because it encourages communication between different scientific fields and acts as a conduit for the exchange of mathematical and computational tools. This paper introduces analogies between concepts and mechanisms from molecular biology and language processing. The main purpose is to find ways for understanding language as a ‘living’, dynamically evolving, self-organizing system. The analogies have been the main source of inspiration for a computational implementation of construction grammar, called Fluid Construction Grammar (FCG). The paper describes briefly the biological analogies underlying FCG and discusses the opportunities for further research that these analogies open up. |
Santos Marques, Tania Filipa ; Beuls, Katrien A Construction Grammar Approach for Pronominal Clitics in European Portuguese Inproceedings Computational Processing of the Portuguese Language, pp. 239-244, Springer Verlag, Germany, 2016, ISBN: 978-3-319-41552-9. Abstract | BibTeX | Tags: Fluid Construction Grammar @inproceedings{0e55431554c9473b948e6b37a3fe8082, title = {A Construction Grammar Approach for Pronominal Clitics in European Portuguese}, author = {Tania Filipa {Santos Marques} and Katrien Beuls}, isbn = {978-3-319-41552-9}, year = {2016}, date = {2016-01-01}, booktitle = {Computational Processing of the Portuguese Language}, pages = {239-244}, publisher = {Springer Verlag}, address = {Germany}, series = {Lecture Notes in Artificial Intelligence}, abstract = {Despite the growing number of Computational Construction Grammar implementations, the field is still lacking evaluation methods to compare grammar fragments across different platforms. Moreover, the hand-crafted nature of most grammars requires profiling tools to understand the complex interactions between constructions of different types. This paper presents a number of evaluation measures, partially based on existing measures in the field of semantic parsing, that are especially relevant for reversible grammar formalisms. The measures are tested on a grammar fragment for European Portuguese clitic placement that is currently under development.}, keywords = {Fluid Construction Grammar}, pubstate = {published}, tppubtype = {inproceedings} } Despite the growing number of Computational Construction Grammar implementations, the field is still lacking evaluation methods to compare grammar fragments across different platforms. Moreover, the hand-crafted nature of most grammars requires profiling tools to understand the complex interactions between constructions of different types. This paper presents a number of evaluation measures, partially based on existing measures in the field of semantic parsing, that are especially relevant for reversible grammar formalisms. The measures are tested on a grammar fragment for European Portuguese clitic placement that is currently under development. |
2013 |
Beuls, Katrien A constructionist approach to student modeling: tracing a student’s constructions through an agent-based tutoring architecture Inproceedings Bradley, Linda; "e, Sylvie Thou (Ed.): EUROCALL Conference proceedings: Learning from the Past, Looking to the Future., pp. 45–50, 2013, ISBN: 978-1-908416-12-4. Abstract | Links | BibTeX | Tags: computer-assisted language learning, construction grammar, Fluid Construction Grammar, intelligent tutoring systems, student modelling @inproceedings{74b47f1c1c5c4a82a4a8696155295000, title = {A constructionist approach to student modeling: tracing a student’s constructions through an agent-based tutoring architecture}, author = {Katrien Beuls}, editor = {Linda Bradley and Sylvie Thou{"e}sny}, doi = {10.14705/rpnet.2013.000137}, isbn = {978-1-908416-12-4}, year = {2013}, date = {2013-01-01}, booktitle = {EUROCALL Conference proceedings: Learning from the Past, Looking to the Future.}, pages = {45--50}, abstract = {Construction Grammar is a well-established linguistic theory that takes the notion of a construction as the basic unit of language. A construction is a symbolic unit that builds up relational form-meaning mappings through a range of language-dependent categorizations. Although the Construction Grammar framework has developed a powerful descriptive and processing model of language, its current practitioners use it mainly to describe specific constructions in a language (from a synchronic or a diachronic perspective) or to theorize about its basic principles. Yet, the potential of Construction Grammar for language teaching or SLA has largely remained ignored, except for a few rare investigations that have confirmed the potential of learning and teaching constructions. Therefore, this paper demonstrates the benefits of adopting the Construction Grammar approach for modelling a student's linguistic knowledge and skills in a language tutoring application. The two major computational implementations of Construction Grammar, Embodied Construction Grammar (ECG) and Fluid Construction Grammar (FCG), have already experimented with simulations of constructional acquisition in first language learning. However, in this paper we propose a tutoring architecture for (adult) second language learning that relies on a student model that consists of the constructions that the student is thought (by the tutor) to have acquired. This student model is embodied in a fully operational student agent, which has a construction inventory, a grammar engine (to process constructions) and learning strategies (to update constructions after learning). The tutoring architecture also contains a tutor agent, which models a competent language user and has the same three components as the student agent. Additionally, the tutor agent has direct access to the student agent's states and can dispose of a range of tutoring strategies. Through linguistic interactions between the real student and the tutor agent, the student agent models the behaviour of the real student and tries to predict his input. The student construction inventory is aligned to the real student's input after every interaction. This innovative architecture, implemented in Fluid Construction Grammar, is demonstrated here for the use case of Spanish past tense expressions, which remains a complex task even for the most advanced learners of Spanish. Through the use of carefully designed diagnostics and repairs we show that the student construction inventory can be updated to maximally approach the real student's linguistic knowledge of the target domain.}, keywords = {computer-assisted language learning, construction grammar, Fluid Construction Grammar, intelligent tutoring systems, student modelling}, pubstate = {published}, tppubtype = {inproceedings} } Construction Grammar is a well-established linguistic theory that takes the notion of a construction as the basic unit of language. A construction is a symbolic unit that builds up relational form-meaning mappings through a range of language-dependent categorizations. Although the Construction Grammar framework has developed a powerful descriptive and processing model of language, its current practitioners use it mainly to describe specific constructions in a language (from a synchronic or a diachronic perspective) or to theorize about its basic principles. Yet, the potential of Construction Grammar for language teaching or SLA has largely remained ignored, except for a few rare investigations that have confirmed the potential of learning and teaching constructions. Therefore, this paper demonstrates the benefits of adopting the Construction Grammar approach for modelling a student's linguistic knowledge and skills in a language tutoring application. The two major computational implementations of Construction Grammar, Embodied Construction Grammar (ECG) and Fluid Construction Grammar (FCG), have already experimented with simulations of constructional acquisition in first language learning. However, in this paper we propose a tutoring architecture for (adult) second language learning that relies on a student model that consists of the constructions that the student is thought (by the tutor) to have acquired. This student model is embodied in a fully operational student agent, which has a construction inventory, a grammar engine (to process constructions) and learning strategies (to update constructions after learning). The tutoring architecture also contains a tutor agent, which models a competent language user and has the same three components as the student agent. Additionally, the tutor agent has direct access to the student agent's states and can dispose of a range of tutoring strategies. Through linguistic interactions between the real student and the tutor agent, the student agent models the behaviour of the real student and tries to predict his input. The student construction inventory is aligned to the real student's input after every interaction. This innovative architecture, implemented in Fluid Construction Grammar, is demonstrated here for the use case of Spanish past tense expressions, which remains a complex task even for the most advanced learners of Spanish. Through the use of carefully designed diagnostics and repairs we show that the student construction inventory can be updated to maximally approach the real student's linguistic knowledge of the target domain. |
2012 |
Wellens, Pieter; Beuls, Katrien; van Trijp, Remi Diagnostics and Repairs in Fluid Construction Grammar Book Chapter Steels, Luc; Hild, Manfred (Ed.): Language Grounding in Robots, pp. 215–234, Springer, 2012, ISBN: 978-1-4614-3063-6, (Luc Steels and Manfred Hild). Abstract | BibTeX | Tags: Fluid Construction Grammar, language processing @inbook{a7007081bd4d433c9c6d89769fb070c7, title = {Diagnostics and Repairs in Fluid Construction Grammar}, author = {Pieter Wellens and Katrien Beuls and Remi van Trijp}, editor = {Luc Steels and Manfred Hild}, isbn = {978-1-4614-3063-6}, year = {2012}, date = {2012-01-01}, booktitle = {Language Grounding in Robots}, pages = {215--234}, publisher = {Springer}, abstract = {Linguistic utterances are full of errors and novel expressions, yet linguistic communication is remarkably robust. This paper presents a double-layered architecture for open-ended language processing, in which 'diagnostics' and 'repairs' operate on a meta-level for detecting and solving problems that may occur during habitual processing on a routine layer. Through concrete operational examples, this paper demonstrates how such an architecture can directly monitor and steer linguistic processing, and how language can be embedded in a larger cognitive system.}, note = {Luc Steels and Manfred Hild}, keywords = {Fluid Construction Grammar, language processing}, pubstate = {published}, tppubtype = {inbook} } Linguistic utterances are full of errors and novel expressions, yet linguistic communication is remarkably robust. This paper presents a double-layered architecture for open-ended language processing, in which 'diagnostics' and 'repairs' operate on a meta-level for detecting and solving problems that may occur during habitual processing on a routine layer. Through concrete operational examples, this paper demonstrates how such an architecture can directly monitor and steer linguistic processing, and how language can be embedded in a larger cognitive system. |
Beuls, Katrien Handling Scope in Fluid Construction Grammar: A Case Study for Spanish Modals Book Chapter Steels, Luc (Ed.): Computational Issues in Fluid Construction Grammar, pp. 123–142, Springer, 2012, ISBN: 978-3-642-34119-9, (Luc Steels). Abstract | BibTeX | Tags: Fluid Construction Grammar, Formal grammar, Modal expressions @inbook{00445b0cfd644ec88ed8df954b4e67c6, title = {Handling Scope in Fluid Construction Grammar: A Case Study for Spanish Modals}, author = {Katrien Beuls}, editor = {Luc Steels}, isbn = {978-3-642-34119-9}, year = {2012}, date = {2012-01-01}, booktitle = {Computational Issues in Fluid Construction Grammar}, pages = {123--142}, publisher = {Springer}, series = {Lecture Notes in Artificial Intelligence}, abstract = {This paper demonstrates one way how the Spanish epistemic modal system can be implemented in Fluid Construction Grammar. Spanish is a Romance language with a rich morpho-phonological system that is characterised by paradigmatic stem changes, a considerable degree of syncretism in verbal suffixes and a sophisticated usage of modal markers. Because the choice of mood does not only depend on the linguistic expression that is used (e.g. "probablemente", "creo que ..."), but also on the position of such expression in the utterance and its scope, the processing engine needs to be flexible enough to capture these conditions. The formal implementation of the Spanish conjugational paradigm with special focus on syncretic markers forms a prerequisite for the processing of verbal mood and modal expressions.}, note = {Luc Steels}, keywords = {Fluid Construction Grammar, Formal grammar, Modal expressions}, pubstate = {published}, tppubtype = {inbook} } This paper demonstrates one way how the Spanish epistemic modal system can be implemented in Fluid Construction Grammar. Spanish is a Romance language with a rich morpho-phonological system that is characterised by paradigmatic stem changes, a considerable degree of syncretism in verbal suffixes and a sophisticated usage of modal markers. Because the choice of mood does not only depend on the linguistic expression that is used (e.g. "probablemente", "creo que ..."), but also on the position of such expression in the utterance and its scope, the processing engine needs to be flexible enough to capture these conditions. The formal implementation of the Spanish conjugational paradigm with special focus on syncretic markers forms a prerequisite for the processing of verbal mood and modal expressions. |
Beuls, Katrien Inflectional patterns as constructions: Spanish verb morphology in Fluid Construction Grammar Journal Article Constructions and Frames, 4 (2), pp. 231–250, 2012, ISSN: 1876-1933. Abstract | BibTeX | Tags: construction morphology, Fluid Construction Grammar, inflectional morphology, rule-based learning, Spanish verbs @article{2b64222a711c425aa5ee1ea109ed63c6, title = {Inflectional patterns as constructions: Spanish verb morphology in Fluid Construction Grammar}, author = {Katrien Beuls}, issn = {1876-1933}, year = {2012}, date = {2012-01-01}, journal = {Constructions and Frames}, volume = {4}, number = {2}, pages = {231--250}, publisher = {John Benjamins Publishing Company}, abstract = {Although often a painful and prolonged process, conjugating verbs correctly is essential when you try to master a foreign language. Verbs that exhibit an irregular conjugation paradigm, however, are often the verbs that occur most frequently in a language. The nature of inflectional morphemes and the mechanism for conjugating verbs have been the topic of debate for 25 years now. This has lead to many different accounts of the problem, both in the field of descriptive linguistics as well as in a range of modeling approaches. The field of Construction Grammar has recently witnessed the theoretical work on Construction Morphology by Geert Booij (2010), but there has been no computational implementation suggested that could test the theory on a large scale. Using the framework of Fluid Construction Grammar (FCG), I investigate the grammar and morphological constructions that are needed to automatically conjugate the full paradigms of the 600 most frequently used verbs in Spanish. This paper reports a fully operational rule-based implementation of such a grammar and goes into the details of the constructions that support it. The results also show that morphological constructions are exemplary constructions since they combine two (or more) units (a stem and a suffix(es)) into a single meaningful unit (a conjugated verb form) that can be picked up by other discourse elements. Extensions towards embedding the conjugation constructions into a bigger grammar or automatically learning new morphological constructions remain the focus of future work.}, keywords = {construction morphology, Fluid Construction Grammar, inflectional morphology, rule-based learning, Spanish verbs}, pubstate = {published}, tppubtype = {article} } Although often a painful and prolonged process, conjugating verbs correctly is essential when you try to master a foreign language. Verbs that exhibit an irregular conjugation paradigm, however, are often the verbs that occur most frequently in a language. The nature of inflectional morphemes and the mechanism for conjugating verbs have been the topic of debate for 25 years now. This has lead to many different accounts of the problem, both in the field of descriptive linguistics as well as in a range of modeling approaches. The field of Construction Grammar has recently witnessed the theoretical work on Construction Morphology by Geert Booij (2010), but there has been no computational implementation suggested that could test the theory on a large scale. Using the framework of Fluid Construction Grammar (FCG), I investigate the grammar and morphological constructions that are needed to automatically conjugate the full paradigms of the 600 most frequently used verbs in Spanish. This paper reports a fully operational rule-based implementation of such a grammar and goes into the details of the constructions that support it. The results also show that morphological constructions are exemplary constructions since they combine two (or more) units (a stem and a suffix(es)) into a single meaningful unit (a conjugated verb form) that can be picked up by other discourse elements. Extensions towards embedding the conjugation constructions into a bigger grammar or automatically learning new morphological constructions remain the focus of future work. |
2011 |
Beuls, Katrien; Steels, Luc Construction sets and unmarked forms: A case study for Hungarian verbal agreement Book Chapter Fried, Mirjam; Ö, Jan-ola (Ed.): Design Patterns in Fluid Construction Grammar, pp. 237–264, John Benjamins Publishing Company, Netherlands, 2011, ISBN: 978-90-272-0433-2, (Mirjam Fried and Jan-Ola Östman). Abstract | BibTeX | Tags: Agreement, Fluid Construction Grammar @inbook{46e7a4ce35724623a70485e7214d2c1b, title = {Construction sets and unmarked forms: A case study for Hungarian verbal agreement}, author = {Katrien Beuls and Luc Steels}, editor = {Mirjam Fried and Jan-ola {Ö}stman}, isbn = {978-90-272-0433-2}, year = {2011}, date = {2011-01-01}, booktitle = {Design Patterns in Fluid Construction Grammar}, pages = {237--264}, publisher = {John Benjamins Publishing Company}, address = {Netherlands}, series = {Constructional Approaches to Language}, abstract = {Construction application can be made more efficient by organizing constructions into sets and by imposing an ordering on when a construction set should be considered. This technique gives us moreover a way to handle unmarked cases, which are abundant in all the world's languages. This paper introduces a non-trivial case study to introduce and illustrate the utility of construction sets, namely Hungarian verbal agreement, which is part of the Hungarian system for expressing argument structure. Hungarian verbal agreement is interesting because it has a dual conjugation system with mono-personal and poly-personal agreement, i.e. agreement with subject only or with subject and object. The choice which system is chosen depends on complex syntactic and semantic considerations. Moreover the morphemes chosen to express agreement and case marking depend on many factors, including the phonological properties of the stem. This chapter therefore illustrates not only how construction sets are useful but also how construction grammar can take multiple linguistic levels into account.}, note = {Mirjam Fried and Jan-Ola Östman}, keywords = {Agreement, Fluid Construction Grammar}, pubstate = {published}, tppubtype = {inbook} } Construction application can be made more efficient by organizing constructions into sets and by imposing an ordering on when a construction set should be considered. This technique gives us moreover a way to handle unmarked cases, which are abundant in all the world's languages. This paper introduces a non-trivial case study to introduce and illustrate the utility of construction sets, namely Hungarian verbal agreement, which is part of the Hungarian system for expressing argument structure. Hungarian verbal agreement is interesting because it has a dual conjugation system with mono-personal and poly-personal agreement, i.e. agreement with subject only or with subject and object. The choice which system is chosen depends on complex syntactic and semantic considerations. Moreover the morphemes chosen to express agreement and case marking depend on many factors, including the phonological properties of the stem. This chapter therefore illustrates not only how construction sets are useful but also how construction grammar can take multiple linguistic levels into account. |
Publications
2024 |
Construction grammar and procedural semantics for human-interpretable grounded language processing Journal Article Linguistics Vanguard, (0), 2024. |
Construction Grammar and Artificial Intelligence Book Chapter Forthcoming Fried, Mirjam; Nikiforidou, Kiki (Ed.): The Cambridge Handbook of Construction Grammar, Cambridge University Press, Cambridge, Forthcoming. |
2023 |
Modelling Language Acquisition through Syntactico-Semantic Pattern Finding Inproceedings Findings of the Association for Computational Linguistics: EACL 2023, pp. 1317-1327, Association for Computational Linguistics, 2023. |
Fluid Construction Grammar: State of the Art and Future Outlook Inproceedings Proceedings of the First International Workshop on Construction Grammars and NLP (CxGs+NLP, GURT/SyntaxFest 2023), pp. 41-50, 2023. |
2022 |
Neural Heuristics for Constructional Language Processing Journal Article Journal of Language Modelling, 10 (2), pp. 287–314, 2022. |
Language Acquisition through Intention Reading and Pattern Finding Inproceedings Proceedings of the 29th International Conference on Computational Linguistics, pp. 15-25, 2022. |
The FCG Editor: An innovative environment for engineering computational construction grammars Journal Article PLOS ONE, 17 (6), pp. 1-27, 2022. |
2021 |
A Computational Construction Grammar Approach to Semantic Frame Extraction Journal Article Linguistics Vanguard, 7 (1), pp. 20180015, 2021. |
2020 |
Making good on a promise: Multi-dimensional constructions Journal Article Belgian Journal of Linguistics, 34 , pp. 357-370, 2020, ISBN: 9789027259851. |
2018 |
Exploring the Creative Potential of Computational Construction Grammar Journal Article Zeitschrift für Anglistik und Amerikanistik, 66 (3), pp. 341–355, 2018, ISSN: 2196-4726. |
2017 |
Basics of Fluid Construction Grammar Journal Article Constructions and frames, 9 (2), pp. 178-255, 2017, ISBN: 1876-1933. |
Robust processing of the Dutch verb phrase Journal Article Constructions and Frames, 9 (2), pp. 226–250, 2017, ISSN: 1876-1933. |
Approaches to the verb phrase in Fluid Construction Grammar Journal Article Constructions and Frames, 9 (2), pp. 175-177, 2017, ISSN: 1876-1933. |
Constructions at Work! Visualising Linguistic Pathways for Computational Construction Grammar Inproceedings Proceedings of the 29th Benelux Conference on Artificial Intelligence, pp. 224–237, 2017. |
Meta-Layer Problem Solving for Computational Construction Grammar Inproceedings The 2017 AAAI Spring Symposium Series, pp. 258–265, 2017, ISBN: 978-1-57735-754-4. |
Russian verbs of motion and their aspectual partners in Fluid Construction Grammar Journal Article Constructions and Frames, 9 (2), pp. 300-318, 2017, ISSN: 1876-1933. |
2016 |
Fluid construction grammar as a biological system Journal Article Linguistics Vanguard, 2 (1), 2016, ISBN: 2199-174X. |
A Construction Grammar Approach for Pronominal Clitics in European Portuguese Inproceedings Computational Processing of the Portuguese Language, pp. 239-244, Springer Verlag, Germany, 2016, ISBN: 978-3-319-41552-9. |
2013 |
A constructionist approach to student modeling: tracing a student’s constructions through an agent-based tutoring architecture Inproceedings Bradley, Linda; "e, Sylvie Thou (Ed.): EUROCALL Conference proceedings: Learning from the Past, Looking to the Future., pp. 45–50, 2013, ISBN: 978-1-908416-12-4. |
2012 |
Diagnostics and Repairs in Fluid Construction Grammar Book Chapter Steels, Luc; Hild, Manfred (Ed.): Language Grounding in Robots, pp. 215–234, Springer, 2012, ISBN: 978-1-4614-3063-6, (Luc Steels and Manfred Hild). |
Handling Scope in Fluid Construction Grammar: A Case Study for Spanish Modals Book Chapter Steels, Luc (Ed.): Computational Issues in Fluid Construction Grammar, pp. 123–142, Springer, 2012, ISBN: 978-3-642-34119-9, (Luc Steels). |
Inflectional patterns as constructions: Spanish verb morphology in Fluid Construction Grammar Journal Article Constructions and Frames, 4 (2), pp. 231–250, 2012, ISSN: 1876-1933. |
2011 |
Construction sets and unmarked forms: A case study for Hungarian verbal agreement Book Chapter Fried, Mirjam; Ö, Jan-ola (Ed.): Design Patterns in Fluid Construction Grammar, pp. 237–264, John Benjamins Publishing Company, Netherlands, 2011, ISBN: 978-90-272-0433-2, (Mirjam Fried and Jan-Ola Östman). |