Elamur Research⌕
☰
home / papers / 2017 / Automatically Tagging Constructions of Causation and Their Slot-Fillers

Automatically Tagging Constructions of Causation and Their Slot-Fillers

Paper · 2017 · Jesse Dunietz, Lori Levin and Jaime Carbonell

Summary

Most shallow semantic parsers assume that meaning attaches to individual lexical units. This assumption breaks down for relations like causation. Causation can surface through verbs, prepositions, conjunctions, adjectives, idioms, or grammatical patterns such as so X that Y, where no single word carries the causal meaning. Drawing on Construction Grammar (CxG), the authors propose a "constructions on top" strategy. They keep a conventional pipeline (POS tagging, dependency parsing) and add a layer that detects meaning-bearing constructions. Machine learning, rather than hand-written specifications, captures the constraints of each construction. Adopting the approach Dunietz et al. (2015) developed for annotating causal language, in which a connective is tagged along with spans for the cause and the effect, the work also releases a new annotated corpus, BECauSE. Two systems are presented: Causeway-S, built on syntactic patterns, and Causeway-L, built on lexical patterns. Both automatically induce patterns that propose candidate connectives and arguments, then filter them with statistical classifiers. Both significantly beat naive baselines on construction recognition and on matching cause/effect heads. This shows that CxG can be made practical inside robust, broad-coverage NLP tooling.

Key points

  • Annotation scheme:
    • Spans: The connective is required and may be discontinuous. Cause and effect spans are optional and only annotated within the same sentence.
    • Exclusions: Untriggered causality, lexical causatives (kill, convince), vague links ("linked to"), and temporal language are left out.
    • Labels: Four causation types (Consequence, Motivation, Purpose, Inference) and a Facilitate/Inhibit distinction are annotated, but the systems do not predict them yet.
  • Pipeline design: Causeway-S matches dependency-tree fragments with slots, while Causeway-L matches lexical patterns. Both combine construction-specific and construction-independent classifiers, with CRF-based argument identification used to resolve pattern ambiguity.
  • Experiments: Three sets assess overall system performance, the contribution of individual design features, and the impact of parsing errors.
  • Motivation versus existing resources: PDTB, PropBank, VerbNet, and FrameNet all restrict triggers to lexical units or particular word classes, so none covers the full range of causal expressions.
  • Released resources: Code is at github.com/duncanka/causeway, and the BECauSE corpus is at github.com/duncanka/BECauSE.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Carnegie Mellon UniversityPittsburgh · United States539 works · 179,533 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

Cite

Cite as Jesse Dunietz, Lori Levin and Jaime Carbonell. 2017. Automatically Tagging Constructions of Causation and Their Slot-Fillers. Transactions of the Association for Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/tacl_a_00050

@article{dunietz2017automatically,
  title = {{Automatically Tagging Constructions of Causation and Their Slot-Fillers}},
  author = {Jesse Dunietz, Lori Levin and Jaime Carbonell},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2017},
  doi = {10.1162/tacl\_a\_00050},
  url = {https://doi.org/10.1162/tacl_a_00050}
}

References

52 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Collin Baker, Michael Ellsworth, and Katrin Erk. 2007. SemEval’07 task 19: frame semantic structure extraction. In Proceedings of the 4th International Workshop on Semantic Evaluations, pages 99–104. Association for Computational Linguistics, Prague, Czech Republic. find
  2. Collin F. Baker, Charles J. Fillmore, and John B. Lowe. 1998. The Berkeley FrameNet Project. In Proceedings of the 17th International Conference on Computational Linguistics, volume 1, pages 86–90. Association for Computational Linguistics, Montreal, Canada.
  3. Timothy Baldwin and Su Nam Kim. 2010. Multiword expressions. In Nitin Indurkhya and Fred J. Damerau, editors, Handbook of Natural Language Processing, volume 2, pages 267–292. CRC Press, Boca Raton, FL. find
  4. Jonathan Berant, Vivek Srikumar, Pei-Chun Chen, Abby Vander Linden, Brittany Harding, Brad Huang, Peter Clark, and Christopher D. Manning. 2014. Modeling biological processes for reading comprehension. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP),…
  5. Benjamin Bergen and Nancy Chang. 2005. Embodied construction grammar in simulation-based language understanding. Construction grammars: Cognitive grounding and theoretical extensions, 3:147–190. find
  6. Steven Bethard, William J Corvey, Sara Klingenstein, and James H. Martin. 2008. Building a corpus of temporal-causal structure. In Proceedings of the 6th International Conference on Language Resources and Evaluation (LREC 2008), pages 908– 915. European Languages Resources Association, Marrakech, Mo… find
  7. Steven Bethard and James H. Martin. 2008. Learning semantic links from a corpus of parallel temporal and causal relations. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies (ACL-08 HLT): Short Papers, pages 177–180. find
  8. Association for Computational Linguistics, Columbus, Ohio. Hans Christian Boas and Ivan A. Sag, editors. 2012. Sign-based construction grammar. CSLI Publications, Stanford, CA. find
  9. Claire Bonial, Julia Bonn, Kathryn Conger, Jena D. Hwang, and Martha Palmer. 2014. PropBank: Semantics of new predicate types. In Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC 2014), pages 3013–3019. European Languages Resources Association, Reykjavik, Ic…
  10. Claire Bonial, Susan Windisch Brown, Jena D. Hwang, Christopher Parisien, Martha Palmer, and Suzanne Stevenson. 2011. Incorporating coercive constructions into a verb lexicon. In Proceedings of the ACL 2011 Workshop on Relational Models of Semantics, pages 72–80. Association for Computational Lingui… find
  11. Juliette Conrath, Stergos Afantenos, Nicholas Asher, and Philippe Muller. 2014. Unsupervised extraction of semantic relations using discourse cues. In Proceedings of the 25th International Conference on Computational Linguistics (COLING 2014), pages 2184–2194. Dublin City University and Association… find
  12. Ann A Copestake and Dan Flickinger. 2000. An open source grammar development environment and broad-coverage English grammar using HPSG. In Proceedings of the 2nd International Conference on Language Resources and Evaluation (LREC 2000), pages 591–600. European Language Resources Association, Athens,… find
  13. Dipanjan Das, Desai Chen, André F.T. Martins, Nathan Schneider, and Noah A. Smith. 2014. Frame-semantic parsing. Computational Linguistics, 40(1):9–56.
  14. Marie-Catherine De Marneffe, Bill MacCartney, Christopher D. Manning, et al. 2006. Generating typed dependency parses from phrase structure parses. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC 2006), volume 6, pages 449–454. European Languages Resou…
  15. Stuart Dreyfus and Robert Wagner. 1971. The Steiner problem in graphs. Networks, 1(3):195–207. find
  16. Jesse Dunietz, Lori Levin, and Jaime Carbonell. 2015. Annotating causal language using corpus lexicography of constructions. In Proceedings of The 9th Linguistic Annotation Workshop (LAW IX), pages 188–196. Association for Computational Linguistics, Denver, CO. find
  17. Charles J. Fillmore. 2012. Encounters with language. Computational Linguistics, 38(4):701–718. find
  18. Charles J. Fillmore, Paul Kay, and Mary Catherine O’Connor. 1988. Regularity and idiomaticity in grammatical constructions: The case of let alone. Language, 64(3):501–538. find
  19. Charles J. Fillmore, Russell Lee-Goldman, and Russell Rhodes. 2012. Sign-based construction grammar, chapter The FrameNet constructicon, pages 309–372. In Boas and Sag (2012). find
  20. Dan Flickinger. 2011. Accuracy vs. robustness in grammar engineering. In Emily M. Bender and Jennifer E. Arnold, editors, Language from a cognitive perspective: Grammar, usage, and processing, volume 201 of CSLI Lecture Notes, pages 31–50. CSLI Publications. find
  21. Roxana Girju. 2003. Automatic detection of causal relations for question answering. In Proceedings of the ACL 2003 workshop on Multilingual summarization and question answering, volume 12, pages 76–83. Association for Computational Linguistics, Sapporo, Japan.
  22. Adele Goldberg. 1995. Constructions: A Construction Grammar Approach to Argument Structure. Chicago University Press, Chicago, IL. find
  23. Cécile Grivaz. 2010. Human judgements on causation in French texts. In Proceedings of the 7th International Conference on Language Resources and Evaluation (LREC 2010), pages 2626–2631. European Languages Resources Association, Valletta, Malta. find
  24. Marti A. Hearst. 1992. Automatic acquisition of hyponyms from large text corpora. In Proceedings of the 14th Conference on Computational Linguistics, volume 2, pages 539–545. Association for Computational Linguistics, Nantes, France.
  25. Christopher Hidey and Kathleen McKeown. 2016. Identifying causal relations using parallel Wikipedia articles. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 1424–1433. Association for Computational Linguistics, Berlin, Germany.
  26. Jena D. Hwang and Martha Palmer. 2015. Identification of caused motion constructions. In Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics (* SEM 2015), pages 51–60. Association for Computational Linguistics, Denver, CO. find
  27. Ashwin Ittoo and Gosse Bouma. 2011. Extracting explicit and implicit causal relations from sparse, domain-specific texts. In Proceedings of the 16th International Conference on Natural Language Processing and Information Systems (NLDB ’11), pages 52–63. Springer-Verlag, Alicante, Spain. find
  28. Paul Jaccard. 1912. The distribution of the flora in the alpine zone. New Phytologist, 11(2):37–50. find
  29. Dan Klein and Christopher D. Manning. 2003. Accurate unlexicalized parsing. In Proceedings of the 41st Annual Meeting on Association for Computational Linguistics, volume 1, pages 423–430. Association for Computational Linguistics, Sapporo, Japan.
  30. Lori Levin, Teruko Mitamura, Davida Fromm, Brian MacWhinney, Jaime Carbonell, Weston Feely, Robert Frederking, Anatole Gershman, and Carlos Ramirez. 2014. Resources for the detection of conventionalized metaphors in four languages. In Proceedings of the 9th International Conference on Language Resou… find
  31. Roger Levy and Galen Andrew. 2006. TRegex and TSurgeon: tools for querying and manipulating tree data structures. In Proceedings of the 5th International Conference on Language Resources and Evaluation (LREC 2006), pages 2231–2234. European Language Resources Association, Genoa, Italy. find
  32. Mitchell Marcus, Grace Kim, Mary Ann Marcinkiewicz, Robert MacIntyre, Ann Bies, Mark Ferguson, Karen Katz, and Britta Schasberger. 1994. The Penn Treebank: Annotating predicate argument structure. In Proceedings of the Workshop on Human Language Technology, HLT ’94, pages 114–119. Association for Co…
  33. Paramita Mirza and Sara Tonelli. 2014. An analysis of causality between events and its relation to temporal information. In Proceedings of the 25th International Conference on Computational Linguistics (COLING 2014), pages 2097–2106. Dublin City University and Association for Computational Linguisti… find
  34. Nasrin Mostafazadeh, Alyson Grealish, Nathanael Chambers, James Allen, and Lucy Vanderwende. 2016. CaTeRS: Causal and temporal relation scheme for semantic annotation of event structures. In Proceedings of the 4th Workshop on Events: Definition, Detection, Coreference, and Representation, pages 51–6… find
  35. Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter, Yoav Goldberg, Jan Hajic, Christopher D. Manning, Ryan McDonald, Slav Petrov, Sampo Pyysalo, Natalia Silveira, Reut Tsarfaty, and Daniel Zeman. 2016. Universal dependencies v1: A multilingual treebank collection. In Proceedings of the 10th Int…
  36. Martha Palmer, Daniel Gildea, and Paul Kingsbury. 2005. The Proposition Bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71–106.
  37. Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, and Édouard Duchesnay. 2011. Scikit-learn… find
  38. Rashmi Prasad, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, Livio Robaldo, Aravind Joshi, and Bonnie Webber. 2008. The Penn Discourse TreeBank 2.0. In Proceedings of the 6th International Conference on Language Resources and Evaluation (LREC 2008), pages 2961–2968. European Language Resources Associat…
  39. Michael Roth and Mirella Lapata. 2015. Context-aware frame-semantic role labeling. Transactions of the Association for Computational Linguistics, 3:449–460.
  40. Evan Sandhaus. 2008. The New York Times annotated corpus. Linguistic Data Consortium. find
  41. Jonathan Schaffer. 2014. The metaphysics of causation. In Edward N. Zalta, editor, The Stanford Encyclopedia of Philosophy. find
  42. Summer 2014 edition. http://plato.stanford.edu/archives/sum2014/entries/ causation-metaphysics/. ↗
  43. Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Meredith Green, Abhijit Suresh, Kathryn Conger, Tim O’Gorman, and Martha Palmer. 2016. A corpus of preposition supersenses. In Proceedings of the 10th Linguistic Annotation Workshop (LAW X), pages 99–109. Association for Computational Linguistics, Ber…
  44. Nathan Schneider, Vivek Srikumar, Jena D. Hwang, and Martha Palmer. 2015. A hierarchy with, of, and for preposition supersenses. In Proceedings of The 9th Linguistic Annotation Workshop (LAW IX), pages 112–123. Association for Computational Linguistics, Denver, CO.
  45. Karin K. Schuler. 2005. VerbNet: A Broad-Coverage, Comprehensive Verb Lexicon. Ph.D. thesis, University of Pennsylvania, Philadelphia, PA. AAI3179808. find
  46. Noah A. Smith, Claire Cardie, Anne Washington, and John Wilkerson. 2014. Overview of the 2014 NLP unshared task in poliinformatics. In Proceedings of the ACL 2014 Workshop on Language Technologies and Computational Social Science, pages 5–7. Association for Computational Linguistics, Baltimore, MD. find
  47. Rion Snow, Daniel Jurafsky, and Andrew Y. Ng. 2005. Learning syntactic patterns for automatic hypernym discovery. In Advances in Neural Information Processing Systems 17 (NIPS 2004), pages 1297– 1304. MIT Press, Vancouver, Canada. find
  48. Luc Steels, editor. 2012. Computational Issues in Fluid Construction Grammar. Lecture Notes in Computer Science. Springer Verlag, Berlin, Germany. find
  49. Oscar Täckström, Kuzman Ganchev, and Dipanjan Das. 2015. Efficient inference and structured learning for semantic role labeling. Transactions of the Association for Computational Linguistics, 3:29– 41.
  50. Masaru Tomita. 1985. An efficient context-free parsing algorithm for natural languages. In Proceedings of the 9th International Joint Conference on Artificial Intelligence (IJCAI), volume 2, pages 756–764. Morgan Kaufmann Publishers Inc., Los Angeles, CA. find
  51. Laure Vieu, Philippe Muller, Marie Candito, and Marianne Djemaa. 2016. A general framework for the annotation of causality based on FrameNet. In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016), pages 3807–3813. European Language Resources Association… find
  52. Phillip Wolff, Bianca Klettke, Tatyana Ventura, and Grace Song. 2005. Expressing causation in English and other languages. In Woo-kyoung Ahn, Robert L. Goldstone, Bradley C. Love, Arthur B. Markman, and Phillip Wolff, editors, Categorization inside and outside the laboratory: Essays in honor of Doug… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/dunietz-2017-automatically-tagging-constructions-causation-their/