Skip to content
Licensed Unlicensed Requires Authentication Published by De Gruyter Mouton February 18, 2021

A computational construction grammar approach to semantic frame extraction

  • Katrien Beuls ORCID logo EMAIL logo , Paul Van Eecke ORCID logo and Vanja Sophie Cangalovic
From the journal Linguistics Vanguard


This paper introduces a novel methodology for extracting semantic frames from text corpora. Building on recent advances in computational construction grammar, the method captures expert knowledge of how semantic frames can be expressed in the form of conventionalised form-meaning pairings, called constructions. By combining these constructions in a semantic parsing process, the frame-semantic structure of a sentence is retrieved through the intermediary of its morpho-syntactic structure. The main advantage of this approach is that state-of-the-art results are achieved, without the need for annotated training data. We demonstrate the method in a case study where causation frames are extracted from English newspaper articles, and compare it to a commonly used approach based on Conditional Random Fields (CRFs). The computational construction grammar approach yields a word-level F1 score of 78.5%, outperforming the CRF approach by 4.5 percentage points.

Corresponding author: Katrien Beuls, Artificial Intelligence Laboratory, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Brussels, Belgium, E-mail:

Funding source: Vlaamse Overheid

Award Identifier / Grant number: 732942

Award Identifier / Grant number: 75929


We would like to thank Luc Steels for his valuable feedback on this work and Remi van Trijp for his work as area editor for Linguistics Vanguard.

  1. Funding: This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 732942 (funder id:, from the Flemish Government under the ‘Onderzoeksprogramma Artificiële Intelligentie (AI) Vlaanderen’ programme, and from a postdoctoral fellowship of the Research Foundation Flanders (FWO) awarded to PVE (grant No 75929, funder id:


Baker, Collin, Charles Fillmore & John Lowe. 1998. The Berkeley FrameNet project. In Proceedings of the 17th International Conference on Computational Linguistics volume 1, 86–90. Association for Computational Linguistics.10.3115/980451.980860Search in Google Scholar

Cohn, Trevor & Philip Blunsom. 2005. Semantic role labelling with tree conditional random fields. In Proceedings of the Ninth Conference on Computational Natural Language Learning, 169–172. Association for Computational Linguistics.10.3115/1706543.1706573Search in Google Scholar

Das, Dipanjan, Desai Chen, André Martins, Nathan Schneider & Noah A Smith. 2014. Frame-semantic parsing. Computational Linguistics 40(1). 9–56.10.1162/COLI_a_00163Search in Google Scholar

Dodge, Ellen, Sean Trott, Luca Gilardi & Elise Stickles. 2017. Grammar scaling: Leveraging FrameNet data to increase embodied construction grammar coverage. In 2017 AAAI Spring Symposia, Stanford University, Palo Alto, California, USA, March 27–29, 2017. Palo Alto: AAAI Press.Search in Google Scholar

Dunietz, Jesse, Lori Levin & Jaime Carbonell. 2017. Automatically tagging constructions of causation and their slot-fillers. Transactions of the Association for Computational Linguistics 5. 117–133.10.1162/tacl_a_00050Search in Google Scholar

Ellsworth, Michael & Adam Janin. 2007. Mutaphrase: Paraphrasing with FrameNet. In Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing, 143–150. Association for Computational Linguistics.10.3115/1654536.1654566Search in Google Scholar

Fillmore, Charles. 1982. Frame semantics. In The Linguistic Society of Korea (ed.), Linguistics in the morning calm, 111–138. Seoul: Hanshin Publishing Co.10.1016/B0-08-044854-2/00424-7Search in Google Scholar

Fillmore, Charles. 1988. The mechanisms of “construction grammar”. In Annual Meeting of the Berkeley Linguistics Society, vol. 14, 35–55.10.3765/bls.v14i0.1794Search in Google Scholar

Fleischman, Michael, Namhee Kwon & Eduard Hovy. 2003. Maximum entropy models for FrameNet classification. In Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing, 49–56. Association for Computational Linguistics.10.3115/1119355.1119362Search in Google Scholar

Gildea, Daniel & Daniel Jurafsky. 2002. Automatic labeling of semantic roles. Computational Linguistics 28(3). 245–288.10.3115/1075218.1075283Search in Google Scholar

Giuglea, Ana-Maria & Alessandro Moschitti. 2006. Semantic role labeling via FrameNet, VerbNet and PropBank. In Proceedings of the 21st International Conference on Computational Linguistics and the 44th Annual Meeting of the Association for Computational Linguistics, 929–936. Association for Computational Linguistics.10.3115/1220175.1220292Search in Google Scholar

Harabagiu, Sanda, Cosmin Bejan & Morarescu Paul. 2005. Shallow semantics for relation extraction. In IJCAI-05, Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, 1061–1066.Search in Google Scholar

He, Luheng, Mike Lewis & Luke Zettlemoyer. 2015. Question-answer driven semantic role labeling: Using natural language to annotate natural language. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 643–653.10.18653/v1/D15-1076Search in Google Scholar

Johansson, Richard & Pierre Nugues. 2007. Lth: semantic structure extraction using nonprojective dependency trees. In Proceedings of the Fourth International Workshop on Semantic Evaluations (SemEval-2007), 227–230.10.3115/1621474.1621522Search in Google Scholar

Marzinotto, Gabriel, Jérémy Auguste, Frédéric Béchet, Géraldine Damnati & Alexis Nasr. 2018. Semantic frame parsing for information extraction : the CALOR corpus. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation, 986–993.Search in Google Scholar

McCallum, Andrew & Wei Li. 2003. Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons. In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL, vol. 4, 188–191. Association for Computational Linguistics.10.3115/1119176.1119206Search in Google Scholar

Micelli, Vanessa, Remi van Trijp & Joachim De Beule. 2009. Framing Fluid Construction Grammar. In Niels Taatgen & Hedderik van Rijn (eds.), In Proceedings of the 31st Annual Conference of the Cognitive Science Society, 3023–3027. Cognitive Science Society.Search in Google Scholar

Ringgaard, Michael, Rahul Gupta & Fernando CN Pereira. 2017. Sling: A framework for frame semantic parsing. arXiv preprint arXiv:1710.07032.Search in Google Scholar

Shen, Dan & Mirella Lapata. 2007. Using semantic roles to improve question answering. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, 12–21. Association for Computational Linguistics.Search in Google Scholar

Shi, Lei & Rada Mihalcea. 2004. An algorithm for open text semantic parsing. In Proceedings of the 3rd Workshop on RObust Methods in Analysis of Natural Language Data, 59–67. Association for Computational Linguistics.10.3115/1621445.1621453Search in Google Scholar

Steels, Luc (ed.). 2011. Design patterns in fluid construction grammar. Amsterdam: John Benjamins.10.1075/cal.11Search in Google Scholar

Thompson, Cynthia, Roger Levy & Christopher Manning. 2003. A generative model for semantic role labeling. In European conference on machine learning, 397–408. Springer.10.1007/978-3-540-39857-8_36Search in Google Scholar

Van Eecke, Paul & Katrien Beuls. 2018. Exploring the creative potential of computational construction grammar. Zeitschrift für Anglistik und Amerikanistik 66(3). 341–355.10.1515/zaa-2018-0029Search in Google Scholar

Received: 2020-02-23
Accepted: 2020-12-21
Published Online: 2021-02-18

© 2021 Walter de Gruyter GmbH, Berlin/Boston

Downloaded on 7.6.2023 from
Scroll to top button