QANom: Question-Answer driven SRL for Nominalizations

What it is about

QANom extends QA-SRL from verbs to nouns derived from verbs: a noun like proof or increase is questioned with its verb's question templates («What has someone proved?», «Why did something increase?») and answered with spans of the sentence. Candidate nouns come from CatVar, WordNet and suffix rules; trained crowd workers first decide whether the noun is used verbally (value in «the value of the pound» is, time in «it's time for…» is not) and then write question–answer pairs. The data has about 10,000 sentences and 26,000 QAs from Wikinews and Wikipedia; consolidated annotations agree at 77 F1 on arguments and 86% on the verbal decision, and against NomBank's deverbal nouns the verbal decision reaches 97% precision and 81% recall. Arguments of nouns are often implicit: 43% are not within two dependency arcs of the noun, against 29% for verbs. A BERT detector reaches 82% on the verbal decision; argument labelling is much harder than for verbs (about 48 F1 unlabelled with predicted predicates).

Ideas

• I1. Test Mova's noun-event decision against QANom's verbal/non-verbal labels: prag/data/nominals.tsv decides by WordNet's first sense and event lexicographer files, without context. Measure its precision and recall on QANom's candidates (tests only, outside the repo, like NOMLEX in world frames nominal-check), and look at the context-dependent misses (value, time, light) for a rule (a determiner + of-phrase reads verbally; time for does not).
• I2. Fill implicit agents of noun events the way QANom's annotators did, by one narrow rule: a noun event in a time or cause phrase of a clause, without its own by/'s agent, takes the clause subject as agent when the verb's selectional restriction allows it («After the escape, the hare ran home» → Event hare escape, linked next to the running). Today noun events are appended without links. Measure the student on «what did the hare do before…» questions and the frame bench with PRAG_VN=score-nouns.
• I3. Reuse QA-SRL's mapping of question templates to roles (subject, object, indirect object, where, when, how, why) as a checklist for Mova's question reader: every template shape should map to the Ask::Role/Ask::Cause Mova uses for the same verb. A table-driven test in prag/src/frames.rs with one question per template on a fixed sentence.

For Mova

11. Nouns and 17-derivation-suffixes.md (deverbal nouns), 30-pragmatics-overview.md §5. Code: prag/data/nominals.tsv, prag/src/vnconv.rs (prag lexicon nominals), prag/src/frames.rs (noun events, question roles), world frames nominal-check. Measures: precision/recall of the noun-event decision, diagnosis shares for questions on events named by nouns, course exams (where noun events gave most).

Topics: Semantic role labeling

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/2020.coling-main.274

@inproceedings{klein2020qanom,
  title = {{QANom: Question-Answer driven SRL for Nominalizations}},
  author = {Klein, Ayal and Mamou, Jonathan and Pyatkin, Valentina and Stepanov, Daniela and He, Hangfeng and Roth, Dan and Zettlemoyer, Luke and Dagan, Ido},
  booktitle = {Proceedings of the 28th International Conference on Computational Linguistics},
  year = {2020},
  doi = {10.18653/v1/2020.coling-main.274},
  url = {https://doi.org/10.18653/v1/2020.coling-main.274}
}

References

41 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Artemis Alexiadou. 2010. Nominalizations: A probe into the architecture of grammar part i: The nominalization puzzle. Language and Linguistics Compass, 4(7):496–511. find
2. Collin F. Baker, Charles J. Fillmore, and John B. Lowe. 1998. The berkeley framenet project. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 1, ACL ’98/COLING ’98, page 86–90, USA. Association for Computational Linguistics. 3078 10 find our card
3. Shany Barhom, Vered Shwartz, Alon Eirew, Michael Bugert, Nils Reimers, and Ido Dagan. 2019. Revisiting joint modeling of cross-document entity and event coreference resolution. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4179–4189. find
4. Yun-Nung Chen, William Yang Wang, and Alexander I Rudnicky. 2013. Unsupervised induction and filling of semantic slots for spoken dialogue systems using frame-semantic parsing. In 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, pages 120–125. IEEE. find
5. Pengxiang Cheng and Katrin Erk. 2018. Implicit argument prediction with event knowledge. 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 831–840. find
6. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. ↗
7. Quynh Ngoc Thi Do, Steven Bethard, and Marie-Francine Moens. 2017. Improving implicit semantic role labeling by predicting semantic frame arguments. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 90–99. find
8. Timothy Dozat and Christopher D. Manning. 2018. Simpler but more accurate semantic dependency parsing. In ACL, pages 484–490. find
9. Nicholas Fitzgerald, Julian Michael, Luheng He, and Luke S. Zettlemoyer. 2018. Large-scale qa-srl parsing. In ACL. find our card
10. Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson Liu, Matthew Peters, Michael Schmitz, and Luke Zettlemoyer. 2018. Allennlp: A deep semantic natural language processing platform. arXiv preprint arXiv:1803.07640. ↗
11. Matthew Gerber and Joyce Y Chai. 2012. Semantic role labeling of implicit arguments for nominal predicates. Computational Linguistics, 38(4):755–798. find
12. Nizar Habash and Bonnie Dorr. 2003. A categorial variation database for english. In Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology-Volume 1, pages 17–23. Association for Computational Linguistics. find
13. Jan Hajic, Massimiliano Ciaramita, Richard Johansson, Daisuke Kawahara, M Antònia Martı́, Lluı́s Màrquez, Adam Meyers, Joakim Nivre, Sebastian Padó, Jan Štěpánek, et al. 2009. The conll-2009 shared task: Syntactic and semantic dependencies in multiple languages. In Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009): Shared Task, pages 1–18. find our card
14. Luheng He, Mike Lewis, and Luke S. Zettlemoyer. 2015. Question-answer driven semantic role labeling: Using natural language to annotate natural language. In EMNLP. find our card
15. Luheng He, Kenton Lee, Omer Levy, and Luke Zettlemoyer. 2018. Jointly predicting predicates and arguments in neural semantic role labeling. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 364–369, Melbourne, Australia, July. Association for Computational Linguistics. find
16. Hangfeng He, Qiang Ning, and Dan Roth. 2020. Quase: Question-answer driven sentence encoding. In Proeedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics. find
17. Zheng Ping Jiang and Hwee Tou Ng. 2006. Semantic role labeling of NomBank: A maximum entropy approach. In Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, pages 138–145, Sydney, Australia, July. Association for Computational Linguistics. find
18. Paul Kingsbury and Martha Palmer. 2002. From treebank to propbank. In LREC, pages 1989–1993. Citeseer. find our card
19. Qi Li, Heng Ji, and Liang Huang. 2013. Joint event extraction via structured prediction with global features. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 73–82. find
20. Catherine Macleod, Ralph Grishman, Adam Meyers, Leslie Barrett, and Ruth Reeves. 1998. Nomlex: A lexicon of nominalizations. In Proceedings of EURALEX, volume 98, pages 187–193. 3079 11 find
21. Adam Meyers, Ruth Reeves, Catherine Macleod, Rachel Szekely, Veronika Zielinska, Brian Young, and Ralph Grishman. 2004a. Annotating noun argument structure for nombank. In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04). find
22. Adam Meyers, Ruth Reeves, Catherine Macleod, Rachel Szekely, Veronika Zielinska, Brian Young, and Ralph Grishman. 2004b. The nombank project: An interim report. In Proceedings of the workshop frontiers in corpus annotation at hlt-naacl 2004, pages 24–31. find
23. Adam Meyers. 2007. Annotation guidelines for nombank-noun argument structure for propbank. Online Publication: http://nlp.cs. nyu. edu/meyers/nombank/nombank-specs-2007. pdf, 44. ↗
24. Julian Michael, Gabriel Stanovsky, Luheng He, Ido Dagan, and Luke Zettlemoyer. 2018. Crowdsourcing question-answer meaning representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 560–568. find our card
25. Simon Mille, Anja Belz, Bernd Bohnet, Yvette Graham, Emily Pitler, and Leo Wanner. 2018. The first multilingual surface realisation shared task (sr’18): Overview and evaluation results. In Proceedings of the First Workshop on Multilingual Surface Realisation, pages 1–12. find our card
26. George A Miller. 1995. Wordnet: a lexical database for english. Communications of the ACM, 38(11):39–41. ↗ our card
27. Stephan Oepen, Marco Kuhlmann, Yusuke Miyao, Daniel Zeman, Silvie Cinková, Dan Flickinger, Jan Hajic, and Zdenka Uresova. 2015. Semeval 2015 task 18: Broad-coverage semantic dependency parsing. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 915–926. find
28. Sebastian Padó, Marco Pennacchiotti, and Caroline Sporleder. 2008. Semantic role assignment for event nominalisations by leveraging verbal data. In Proceedings of the 22nd International Conference on Computational Linguistics-Volume 1, pages 665–672. Association for Computational Linguistics. find
29. 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
30. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Hwee Tou Ng, Anders Björkelund, Olga Uryupina, Yuchen Zhang, and Zhi Zhong. 2013. Towards robust linguistic analysis using OntoNotes. In Proceedings of the Seventeenth Conference on Computational Natural Language Learning, pages 143–152, Sofia, Bulgaria, August. Association for Computational Linguistics. find
31. Pranav Rajpurkar, Robin Jia, and Percy Liang. 2018. Know what you don’t know: Unanswerable questions for squad. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 784–789. find
32. Paul Roit, Ayal Klein, Daniela Stepanov, Jonathan Mamou, Julian Michael, Gabriel Stanovsky, Luke Zettlemoyer, and Ido Dagan. 2020. Controlled crowdsourcing for high-quality QA-SRL annotation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7008–7013, Online, July. Association for Computational Linguistics. find our card
33. Liliana Mamani Sánchez and Claudia Oliveira. 2017. Deverbal noun complementation rules applied to semantic role labeling. Revista da ABRALIN, 7(2). find
34. Peng Shi and Jimmy Lin. 2019. Simple bert models for relation extraction and semantic role labeling. arXiv preprint arXiv:1904.05255. ↗
35. Gabriel Stanovsky and Ido Dagan. 2016. Creating a large benchmark for open information extraction. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2300–2305. find
36. Gabriel Stanovsky, Julian Michael, Luke Zettlemoyer, and Ido Dagan. 2018. Supervised open information extraction. 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 885–895. find
37. Emma Strubell, Patrick Verga, Daniel Andor, David Weiss, and Andrew McCallum. 2018. Linguistically-informed self-attention for semantic role labeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 5027–5038. find
38. Zhixing Tan, Mingxuan Wang, Jun Xie, Yidong Chen, and Xiaodong Shi. 2018. Deep semantic role labeling with self-attention. In Thirty-Second AAAI Conference on Artificial Intelligence. 3080 12 1 2 3 4 5 6 WH Who How What What Who What AUX has did has has been did did SUBJ someone someone someone someone VERB proven prove proven proven prove prove OBJ1 something something something PREP OBJ2\MISC by about about someone someone ? ? ? ? ? ? ? *Table 8: Examples for QA-SRL questions decomposed into their slot-based template. Refer to (He et al., 2015) for the full description. Questions 3 and 4 capture the same role, while 5–6 jointly represent an alternative annotation which decomposes their answer span (God existence) into two answer (God, Existence).* Diana Trandabăţ. 2011. Using semantic roles to improve summaries. In Proceedings of the 13th European Workshop on Natural Language Generation, pages 164–169. Association for Computational Linguistics. find
39. Christopher Walker, Stephanie Strassel, Julie Medero, and Kazuaki Maeda. 2006. Ace 2005 multilingual training corpus. Linguistic Data Consortium, Philadelphia, 57:45. find
40. Hai Wang, Mohit Bansal, Kevin Gimpel, and David McAllester. 2015. Machine comprehension with syntax, frames, and semantics. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), volume 2, pages 700–706. find
41. Yanpeng Zhao and Ivan Titov. 2020. Unsupervised transfer of semantic role models from verbal to nominal domain. arXiv preprint arXiv:2005.00278. ↗

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/klein-2020-qanom-question-answer-driven-srl/