The Possible, the Plausible, and the Desirable: Event-Based Modality Detection for Language Processing

What it is about

The paper defines event-based modality detection: find every modal trigger in a sentence, of any part of speech (should, plan, prefers, probably, necessary, able), give it a sense, and link it to the head of the event it modifies. The senses form a two-level taxonomy simplified from the Georgetown Gradable Modal Expressions scheme: Plausibility (state of knowledge — epistemic; state of the world — circumstantial; abilities of an agent — dynamic) and Priority (rules and norms — deontic; desires; plans and goals — teleological). Modality is kept separate from factuality: «She was able to reach the shore» and «The paper announced she reached the shore» share a factual event but differ in perspective. On the GME corpus (11K news sentences; triggers in 48% of sentences, 1,502 trigger types, only 37% verbs; human agreement α 0.89 for the two top classes, 0.49 for fine senses) RoBERTa taggers find triggers and senses well for auxiliaries and much less well for open-class triggers, and knowing the trigger helps to find the modified event.

Ideas

• I1. Add a modal-perspective field to Mova's frames, separate from neg/cond and from factuality: ability (can, able to, manage), possibility (may, perhaps, likely), norm (should, must, ought, it is wrong to), desire (want, wish, hope), plan (plan to, intend, in order to). The trigger can be a verb, adjective, noun or adverb attached to the event head in the tree; record the trigger word as the reason. Code in prag/src/frames.rs; trigger list in prag/data.
• I2. Route school questions by this field: «Could the fox reach the grapes?» asks ability, «Should the boy have lied?» asks a norm, «What did the hare plan?» asks a plan. The religion-ethics and reflection courses are full of norm questions; count with world knowledge diagnose how many of their failures are questions whose remembered frames carry a modal the reader dropped.
• I3. Use the paper's two-level structure for evaluation: first get Plausibility vs Priority right (high human agreement), and report the fine senses only as a second figure, since even experts agree on them at α 0.49. Same rule for the teacher: ask for the coarse class in silver, not the fine one.

For Mova

13. Verbs (modals), 32-politeness-and-hedging.md §8 (epistemic modality), 33-implicature-and-presupposition.md. Code: prag/src/frames.rs (modal field), prag/data (trigger list), world/src/knowledge.rs (question routing). Measures: frame bench (no loss), course test counts on ethics and reflection courses.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/2021.acl-long.77

@inproceedings{pyatkin2021possible,
  title = {{The Possible, the Plausible, and the Desirable: Event-Based Modality Detection for Language Processing}},
  author = {Pyatkin, Valentina and Sadde, Shoval and Rubinstein, Aynat and Portner, Paul and Tsarfaty, Reut},
  booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  year = {2021},
  doi = {10.18653/v1/2021.acl-long.77},
  url = {https://doi.org/10.18653/v1/2021.acl-long.77}
}

References

41 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Kathryn Baker, Michael Bloodgood, Bonnie J. Dorr, Chris Callison-Burch, Nathaniel W. Filardo, Christine Piatko, Lori Levin, and Scott Miller. 2012. Use of modality and negation in semantically-informed syntactic MT. Computational Linguistics, 38(2):411–438. find
2. Jon Barwise and John Perry. 1981. Situations and attitudes. The Journal of Philosophy, 78(11):668–691. find
3. Lucia Donatelli, Michael Regan, William Croft, and Nathan Schneider. 2018. Annotation of tense and aspect semantics for sentential AMR. In Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018), pages 96–108, Santa Fe, New Mexico, USA. Association for Computational Linguistics. find our card
4. Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson F Liu, Matthew Peters, Michael Schmitz, and Luke Zettlemoyer. 2018. Allennlp: A deep semantic natural language processing platform. In Proceedings of Workshop for NLP Open Source Software (NLP-OSS), pages 1–6. find
5. Elisa Ghia, Lennart Kloppenburg, Malvina Nissim, and Paola Pietrandrea. 2016. A construction-centered approach to the annotation of modality. In Twelfth Joint ACL - ISO Workshop on Interoperable Semantic Annotation (ISA-12), pages 67–74, Portorož, Slovenia. find
6. Valentine Hacquard. 2010. On the event relativity of modal auxiliaries. Natural Language Semantics, 18:79–114. find
7. Iris Hendrickx, Amália Mendes, and Silvia Mencarelli. 2012. Modality in text: a proposal for corpus annotation. In Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC’12), Istanbul, Turkey. European Language Resources Association (ELRA). find
8. Matthew Honnibal, Ines Montani, Sofie Van Lan-deghem, and Adriane Boyd. 2020. spaCy: Industrial-strength Natural Language Processing in Python. find
9. Angelika Kratzer. 1981. The notional category of modality. In Hans-Jürgen Eikmeyer and Hannes Rieser, editors, Words, Worlds, and Contexts, pages 38–74. Walter de Gruyter, Berlin. Reprinted in Formal Semantics: The Essential Readings, ed. find
10. Paul Portner and Barbara H. Partee (2002), 289–323. Oxford: Blackwell. find
11. Angelika Kratzer. 2010. Situations in natural language semantics. In Edward N. Zalta, editor, The Stanford Encyclopedia of Philosophy, fall 2010 edition. First published February 2007. find
12. Saul A. Kripke. 1959. A completeness theorem in modal logic. The Journal of Symbolic Logic, 24(1):1–14. find
13. Julia Lavid, Marta Carretrero, and Juan Rafael Zamorano-Mansilla. 2016. A linguistically-motivated annotation model of modality in English and Spanish: Insights from MULTINOT. In Linguistic Issues in Language Technology, Volume 14, 2016 - Modality: Logic, Semantics, Annotation, and Machine Learning. CSLI Publications. find
14. David Lewis. 1973. Counterfactuals. Harvard University Press, Cambridge, Mass. find
15. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692. ↗
16. Ashutosh Malhotra, Erfan Younesi, Harsha Gurulingappa, and Martin Hofmann-Apitius. 2013. ‘Hy-pothesisFinder:’ a strategy for the detection of speculative statements in scientific text. PLOS Computational Biology, 9(7):e1003117. find
17. Ana Marasović and Anette Frank. 2016. Multilingual modal sense classification using a convolutional neural network. In Proceedings of the 1st Workshop on Representation Learning for NLP, pages 111–120. find
18. Ana Marasović, Mengfei Zou, Alexis Palmer, and Anette Frank. 2016. Modal sense classification at large. paraphrase-driven sense projection, semantically enriched classification models and cross-genre evaluations. LiLT (Linguistic Issues in Language Technology), 14. find
19. Lisa Matthewson and Hubert Truckenbrodt. 2018. Modal flavour/modal force interactions in German: soll, sollte, muss and müsste. Linguistische Berichte, 255:259–312. find
20. Amália Mendes, Iris Hendrickx, Liciana Ávila, Paulo Quaresma, Teresa Gonçalves, and João Sequeira. 2016. Modality annotation for Portuguese: from manual annotation to automatic labeling. In Linguistic Issues in Language Technology, Volume 14, 2016 - Modality: Logic, Semantics, Annotation, and Machine Learning. CSLI Publications. find
21. Makoto Miwa, Paul Thompson, John McNaught, Douglas B. Kell, and Sophia Ananiadou. 2012. Extracting semantically enriched events from biomedical literature. BMC Bioinformatics, 13(108). find
22. Roser Morante and Caroline Sporleder. 2012. Modality and negation: An introduction to the special issue. Computational Linguistics, 38(2):223–260. find
23. Malvina Nissim, Paola Pietrandrea, Andrea Sansò, and Caterina Mauri. 2013. Cross-linguistic annotation of modality: a data-driven hierarchical model. In Proceedings of the 9th Joint ISO - ACL SIGSEM Workshop on Interoperable Semantic Annotation, pages 7–14, Potsdam, Germany. Association for Computational Linguistics. find
24. Frank R. Palmer. 1986. Mood and Modality. Cambridge University Press, Cambridge. find
25. Terence Parsons. 1990. Events in the Semantics of English: A Study in Subatomic Semantics. MIT Press, Cambridge, MA. find
26. Jeffrey Pennington, Richard Socher, and Christopher D Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532–1543. find
27. Paul Portner. 2009. Press. Modality. find
28. Oxford University Mario Prieto, Helena Deus, Anita de Waard, Erik Schultes, Beatriz García-Jiménez, and Mark D. Wilkinson. 2020. Data-driven classification of the certainty of scholarly assertions. PeerJ 8, 8:e8871. find
29. Paulo Quaresma, Amália Mendes, Iris Hendrickx, and Teresa Gonçalves. 2014. Automatic tagging of modality: identifying triggers and modal value. In The 10th Joint ACL SIGSEM - ISO Workshop on Interoperable Semantic Annotation, pages 95–102. find
30. Victoria L. Rubin. 2010. Epistemic modality: From uncertainty to certainty in the context of information seeking as interactions with texts. Information Processing & Management, 46(5):533–540. find
31. Aynat Rubinstein. 2012. Roots of Modality. Ph.D. thesis, University of Massachusetts Amherst. find
32. Aynat Rubinstein, Hillary Harner, Elizabeth Krawczyk, Dan Simonson, Graham Katz, and Paul Portner. 2013. Toward fine-grained annotation of modality in text. In Proceedings of the IWCS 2013 Workshop on Annotation of Modal Meanings in Natural Language (WAMM), pages 38–46. find
33. Rachel Rudinger, Aaron Steven White, and Benjamin Van Durme. 2018. Neural models of factuality. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 731–744, New Orleans, Louisiana. Association for Computational Linguistics. find our card
34. Josef Ruppenhofer and Ines Rehbein. 2012. Yes we can!? annotating english modal verbs. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC-2012), pages 1538–1545. find
35. Erik Tjong Kim Sang and Sabine Buchholz. 2000. Introduction to the conll-2000 shared task chunking. In Fourth Conference on Computational Natural Language Learning and the Second Learning Language in Logic Workshop. find
36. Roser Saurí and James Pustejovsky. 2009. FactBank: a corpus annotated with event factuality. Language Resources and Evaluation, 43:227–268. find
37. Veronika Vincze, György Szarvas, Richárd Farkas, György Móra, and János Csirik. 2008. The Bio-Scope corpus: biomedical texts annotated for uncertainty, negation and their scopes. BMC Bioinformatics, 9:S9. find
38. Janyce Wiebe, Theresa Wilson, and Claire Cardie. 2005. Annotating expressions of opinions and emotions in language. Language Resources and Evaluation, 39(2-3):165–210. find
39. Jie Yang and Yue Zhang. 2018. NCRF++: An open-source neural sequence labeling toolkit. arXiv preprint arXiv:1806.05626. ↗
40. Chrysoula Zerva, Riza Batista-Navarro, Philip Day, and Sophia Ananiadou. 2017. Using uncertainty to link and rank evidence from biomedical literature for model curation. Bioinformatics, 33(23):3784–3792. find
41. Mengfei Zhou, Anette Frank, Annemarie Friedrich, and Alexis Palmer. 2015. Semantically enriched models for modal sense classification. In Proceedings of the First Workshop on Linking Computational Models of Lexical, Sentential and Discourse-level Semantics, pages 44–53, Lisbon, Portugal. Association for Computational Linguistics. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/pyatkin-2021-possible-plausible-desirable-event-based/