Elamur Research⌕
☰
home / papers / 2022 / Text-based NP Enrichment

Text-based NP Enrichment

Paper · 2022 · Yanai Elazar, Victoria Basmov, Yoav Goldberg et al.

Summary

Standard NLP tasks capture only some of the ways entities in a text relate. Semantic role labeling covers links mediated by verbs, and coreference covers identity. Many noun-to-noun connections, whether stated or only implied through prepositions, are left out. The authors propose Text-based NP Enrichment (TNE). For every ordered pair of non-pronominal base-NPs in a document, a system decides whether a preposition-mediated relation holds. If it does, the system picks the preposition that fits best. The output is a set of triplets: anchor, preposition, complement.

Prepositions are ambiguous, but using them as labels keeps the task tightly scoped. It also makes the task easy for crowd annotators and downstream users to understand. The authors built a large English dataset of multi-paragraph documents, analyzed it, and fine-tuned pre-trained language models as baselines. These models score only moderately and stay far below human performance. Most relations are implicit and need world knowledge or reasoning across the document. TNE matters both as a reading-comprehension benchmark and as a reusable component for relation and event extraction, QA and retrieval.

Key points

  • Dataset: about 5.5K documents with over 1M NP links, plus high-quality in-domain and out-of-domain test sets. Data, code, models, a demo and a leaderboard are available at yanaiela.github.io/TNE/.

  • Document statistics: each document spans 3 paragraphs and contains on average 35.8 NPs and 186.7 preposition-mediated relations. Most of these relations are implicit.

  • Task setup:

    • NPs are base-NPs (NP chunks, following Ramshaw and Marcus, 1995).
    • Both directions of each pair are candidates, giving k²−k pairs for k NPs.
    • An extra "member-of" label was added to reduce annotator confusion. It is kept in the data but is not officially part of the task.

  • Baselines: fine-tuned pre-trained LMs achieve moderate results, with a large gap to humans.

  • Relation to bridging anaphora: TNE differs in several ways.

    • It covers both explicit and implicit links.
    • Anchors may be discourse-old.
    • Both sides of a relation must be NPs.
    • It is simple enough for crowd annotation, which bridging is not.

    The authors also relate TNE to decontextualization (Choi et al., 2021).

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

🔬Allen Institute for Artificial IntelligenceSeattle · United States275 works · 97,634 citations🎓Bar-Ilan UniversityRamat Gan · Israel141 works · 23,225 citations

 Fields, topics and concepts

📚 Shelves 5The 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 worksComputer Vision and Pattern Recognition · 2,869 works

Cite

Cite as Yanai Elazar, Victoria Basmov, Yoav Goldberg and Reut Tsarfaty. 2022. Text-based NP Enrichment. 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_00488

@article{elazar2022text,
  title = {{Text-based NP Enrichment}},
  author = {Yanai Elazar, Victoria Basmov, Yoav Goldberg and Reut Tsarfaty},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2022},
  doi = {10.1162/tacl\_a\_00488},
  url = {https://doi.org/10.1162/tacl_a_00488}
}

References

69 references, 40 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Christian Barker. 1995. Possessive Descriptions, Dissertations in linguistics. Center for the Study of Language and Information. Bibliogr. pages 189–194. find
  2. Robyn Carston. 2009. The explicit/implicit distinction in pragmatics and the limits of explicit communication. International Review of Pragmatics, 1:35–62. https://doi.org/10.1163/187731009X455839 ↗
  3. Arie Cattan, Alon Eirew, Gabriel Stanovsky, Mandar Joshi, and Ido Dagan. 2021. Realistic evaluation principles for cross-document coreference resolution. In Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics, pages 143–151, Online. Association for Computation…
  4. Gottlob Frege. 1960. On sense and reference. In Darragh Byrne and Max Kölbel, editors, Arguing About Language, pages 36–56. Routledge. find
  5. Claire Gardent, Hélène Manuélian, and Eric Kow. 2003. Which bridges for bridging definite descriptions? In Proceedings of 4th International Workshop on Linguistically Interpreted Corpora (LINC-03) at EACL 2003.
  6. Pengxiang Cheng and Katrin Erk. 2019. Implicit argument prediction as reading comprehension. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 6284–6291. https://doi.org/10 .1609/aaai.v33i01.33016284 find
  7. 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, Melbourne,…
  8. Eunsol Choi, Jennimaria Palomaki, Matthew Lamm, Tom Kwiatkowski, Dipanjan Das, and Michael Collins. 2021. Decontextualization: Making sentences stand-alone. Transactions of the Association for Computational Linguistics, 9:447–461. https://doi.org/10.1162/tacl_a_00377 ↗
  9. Christopher Clark, Kenton Lee, Ming-Wei Chang, Tom Kwiatkowski, Michael Collins, and Kristina Toutanova. 2019. Boolq: Exploring the surprising difficulty of natural yes/no questions. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:…
  10. Matthew Gerber and Joyce Y. Chai. 2012. Semantic role labeling of implicit arguments for nominal predicates. Computational Linguistics, 38(4):755–798. https://doi.org/10.1162/COLI a 00110 ↗
  11. Herbert H. Clark. 1975. Bridging. In Theoretical Issues in Natural Language Processing. https://doi.org/10.3115/980190.980237 — [doi:10.3115/980190.980237](https://doi.org/10.3115/980190.980237) ↗
  12. Jos De Bruin and Remko Scha. 1988. The interpretation of relational nouns. In 26th Annual Meeting of the Association for Computational Linguistics, pages 25–32. https://doi.org/10.3115/982023.982027 ↗
  13. Luke Gessler, Shira Wein, and Nathan Schneider. 2021. Supersense and sensibility: Proxy tasks for semantic annotation of prepositions. In SCIL. find
  14. Daniel Gildea and Daniel Jurafsky. 2002. Automatic labeling of semantic roles. Computational Linguistics, 28(3):245–288. https://doi.org/10.1162/089120102760275983 ↗
  15. Yulia Grishina. 2016. Experiments on bridging across languages and genres. In Proceedings of the Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2016), pages 7–15, San Diego, California. Association for Computational Linguistics. https://doi.org/10 .18653/v1/W16-0702
  16. Jesse Dunietz, Greg Burnham, Akash Bharadwaj, Owen Rambow, Jennifer Chu-Carroll, and Dave Ferrucci. 2020. To test machine comprehension, start by defining comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7839–7859. https://doi.org/10 .1… find
  17. Ralph Grishman and Beth Sundheim. 1996. Message Understanding Conference-6: A brief history. In Proceedings of the 16th Conference on Computational Linguistics - Volume 1, COLING ’96, pages 466–471, USA. Association for Computational Linguistics. https://doi.org/10.3115/992628.992709 ↗
  18. Nicholas FitzGerald, Julian Michael, Luheng He, and Luke Zettlemoyer. 2018. Large-scale QA-SRL parsing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Luheng He, Mike Lewis, and Luke Zettlemoyer. 2015. Question-answer driven semant…
  19. Association for Computational Linguistics: Human Language Technologies, pages 907–917, Atlanta, Georgia. Association for Computational Linguistics. find
  20. Yufang Hou, Katja Markert, and Michael Strube. 2014. A rule-based system for unrestricted bridging resolution: Recognizing bridging anaphora and finding links to antecedents. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2082–2093, Doha, Qat…
  21. Matthew Honnibal, Ines Montani, Sofie Van Landeghem, and Adriane Boyd. 2020. spaCy: Industrial-strength natural language processing in Python. find
  22. Yufang Hou. 2018a. A deterministic algorithm for bridging anaphora resolution. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1938–1948, Brussels, Belgium. Association for Computational Linguistics. https://doi.org/10.18653/v1/D18-1219 ↗
  23. Yufang Hou, Katja Markert, and Michael Strube. 2018. Unrestricted bridging resolution. Computational Linguistics, 44(2):237–284. https://doi.org/10.1162/coli a 00315 ↗
  24. Yufang Hou. 2018b. Enhanced word representations for bridging anaphora resolution. 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 1–7, New Orleans, Louisiana. Associatio…
  25. Marwan Jarrah. 2016. Explicit-implicit distinction: A review of related literature. Advances in Language and Literary Studies, 7:175–184. https://doi.org/10.7575/aiac.alls.v .7n.1p.175 — [doi:10.7575/aiac.alls.v](https://doi.org/10.7575/aiac.alls.v) ↗
  26. Yufang Hou. 2020. Bridging anaphora resolution as question answering. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1428–1438. https://doi.org/10.18653/v1/2020 .acl-main.132 ↗
  27. Yufang Hou. 2021. End-to-end neural information status classification. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1377–1388. https://doi.org/10.18653/v1/2021.findings -emnlp.119 ↗
  28. Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, and Omer Levy. 2020. SpanBERT: Improving pre-training by representing and predicting spans. Transactions of the Association for Computational Linguistics, 8:64–77. https://doi.org/10 .1162/tacl_a_00300
  29. D. Jurafsky and J. H. Martin. 2009. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, Prentice Hall Series in Artificial Intelligence. Pearson Prentice Hall. find
  30. Divyansh Kaushik and Zachary C. Lipton. 2018. How much reading does reading comprehension require? A critical investigation of popular benchmarks. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 5010–5015. https://doi.org/10.18653/v1/D18 -1546 ↗
  31. Yufang Hou, Katja Markert, and Michael Strube. 2013a. Cascading collective classification for bridging anaphora recognition using a rich linguistic feature set. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 814–820, Seattle, Washington, USA. Associa…
  32. Katherine Keith, Abram Handler, Michael Pinkham, Cara Magliozzi, Joshua McDuffie, and Brendan O’Connor. 2017. Identifying civilians killed by police with distantly supervised entity-event extraction. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 154… find
  33. Tomoko Matsui. 2001. Experimental pragmatics: Towards testing relevance-based predictions about anaphoric bridging inferences. In International and Interdisciplinary Conference on Modeling and Using Context, pages 248–260. Springer. https://doi.org/10.1007/3 -540-44607-9 19 — [doi:10.1007/3](https://doi.org/10.1007/3) find
  34. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7–9, 2015, Conference Track Proceedings.
  35. A. Meyers, R. Reeves, C. Macleod, R. Szekely, V. Zielinska, B. Young, and R. Grishman. 2004. Annotating noun argument structure for Nom-Bank. In Proceedings of LREC-2004, Lisbon, Portugal. find
  36. Ayal Klein, Jonathan Mamou, Valentina Pyatkin, Daniela Stepanov, Hangfeng He, Dan Roth, Luke Zettlemoyer, and Ido Dagan. 2020. QANom: Question-answer driven SRL for nominalizations. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3069–3083, Barcelona, Spain (O…
  37. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S. Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K. Q. Weinberger, editors, Advances in Neural Information Processing Systems 26, p…
  38. Hideo Kobayashi and Vincent Ng. 2021. Bridging resolution: Making sense of the state of the art. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1652–1659. https://doi.org/10.18653/v1/2021.naacl… ↗
  39. Anna Nedoluzhko. 2013. Generic noun phrases and annotation of coreference and bridging relations in the Prague dependency treebank. In Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse, pages 103–111, Sofia, Bulgaria. Association for Computational Linguistics… find
  40. Edward Newell and Jackie C. K. Cheung. 2018. Constructing a lexicon of relational nouns. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA). find
  41. Sebastian Löbner. 2015. Functional concepts and frames. In Meanings, Frames, and Conceptual Representation, page 15–42, Düsseldorf. Düsseldorf University Press. find
  42. Janis Pagel and Ina Roesiger. 2018. Towards bridging resolution in German: Data analysis and rule-based experiments. In Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference, pages 50–60, New Orleans, Louisiana. Association for Computational Linguistics. ht… find
  43. Sebastian Loebner. 1985. Definites. Journal of Semantics, 4. https://doi.org/10.1093/jos/4.4.279 ↗
  44. Sebastian Loebner. 1998. Definite associative anaphora. In Approaches to Discourse Anaphora. Proceedings of DAARC96 – Discourse Anaphora and Resolution Colloquium, Lancaster. Lancaster University. find
  45. Martha Palmer, Daniel Gildea, and Paul Kingsbury. 2005. The proposition bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71–106. https://doi.org/10.1162/0891201053630264 ↗
  46. Katja Markert, Yufang Hou, and Michael Strube. 2012. Collective classification for fine-grained information status. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 795–804, Jeju Island, Korea. Association for Computational Lin…
  47. Martha Palmer, Daniel Gildea, and Nianwen Xue. 2010. Semantic Role Labeling, Synthesis Lectures on Human Language Technology Series, Morgan and Claypool. https://doi.org/10.2200/S00239ED1V01Y200912 HLT006 — [doi:10.2200/s00239ed1v01y200912](https://doi.org/10.2200/s00239ed1v01y200912) ↗
  48. Lance Ramshaw and Mitch Marcus. 1995. Text chunking using transformation-based learning. In Third Workshop on Very Large Corpora.
  49. Onkar Arun Pandit and Yufang Hou. 2021. Probing for bridging inference in transformer language models. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4153–4163. https://doi.org/10 .18653/v1/2021… find
  50. Ina Roesiger, Maximilian Köper, Kim Anh Nguyen, and Sabine Schulte im Walde. 2018a. Integrating predictions from neural-network relation classifiers into coreference and bridging resolution. In Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference, pages 4…
  51. Barbara Partee. 1983/1997. Uniformity vs. versatility: The genitive, a case study. Appendix to Theo Janssen, 1997. In Johan Benthem and Alice Meulen, editors, Compositionality. The Handbook of Logic and Language, pages 464–70. Elsevier. find
  52. Ina Roesiger, Arndt Riester, and Jonas Kuhn. 2018b. Bridging resolution: Task definition, corpus resources and rule-based experiments. In Proceedings of the 27th International Conference on Computational Linguistics, pages 3516–3528, Santa Fe, New Mexico, USA. Association for Computational Linguisti…
  53. Barbara Partee, and V. Borschev. 2000. Genitives, relational nouns, and the argument-modifier distinction. ZAS Papers in Linguistics, 17. https://doi.org/10.21248/zaspil .17.2000.46 — [doi:10.21248/zaspil](https://doi.org/10.21248/zaspil) ↗
  54. 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,…
  55. Massimo Poesio and Renata Vieira. 1998. A corpus-based investigation of definite description use. Computational Linguistics, 24(2):183–216.
  56. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. CoNLL-2012 shared task: Modeling multilingual unrestricted coreference in Onto-Notes. In Joint Conference on EMNLP and CoNLL-Shared Task, pages 1–40. find
  57. Ina Rösiger. 2018a. Bashi: A corpus of Wall Street Journal articles annotated with bridging links. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018).
  58. Valentina Pyatkin, Ayal Klein, Reut Tsarfaty, and Ido Dagan. 2020. Qadiscourse-discourse relations as qa pairs: Representation, crowdsourcing and baselines. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2804–2819. https://doi.org/10 .18653/v…
  59. Ina Rösiger. 2018b. Rule- and learning-based methods for bridging resolution in the ARRAU corpus. In Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference, pages 23–33, New Orleans, Louisiana. Association for Computational Linguistics. https://doi.org/10 .…
  60. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. Squad: 100,000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2383–2392. https://doi.org/10.18653/v1/D16 -1264 ↗
  61. Josef Ruppenhofer, Michael Ellsworth, Myriam Schwarzer-Petruck, Christopher R. Johnson, and Jan Scheffczyk. 2016. Framenet II: Extended theory and practice, Technical report, International Computer Science Institute. find
  62. Josef Ruppenhofer, Caroline Sporleder, Roser Morante, Collin Baker, and Martha Palmer. 2009. SemEval-2010 task 10: Linking events and their participants in discourse. In Proceedings of the Workshop on Semantic Evaluations: Recent Achievements and Future Directions (SEW-2009), pages 106–111, Boulder,…
  63. Linguistics. https://doi.org/10.3115/v1/W15-1612 ↗
  64. Ian Tenney, Patrick Xia, Berlin Chen, Alex Wang, Adam Poliak, R Thomas McCoy, Najoung Kim, Benjamin Van Durme, Samuel R. Bowman, Dipanjan Das, and Ellie Pavlick. 2018. What do you learn from context? Probing for sentence structure in contextualized word representations. In International Conference o…
  65. 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, pages 99–109, Berlin, Germany. Association for Computational Linguis…
  66. Olga Uryupina, Ron Artstein, Antonella Bristot, Federica Cavicchio, Francesca Delogu, Kepa J. Rodriguez, and Massimo Poesio. 2019. Annotating a broad range of anaphoric phenomena, in a variety of genres: The ARRAU corpus. Natural Language Engineering, 26:1–34. https://doi.org/10.1017/S1351324919 000… — [doi:10.1017/s1351324919](https://doi.org/10.1017/s1351324919) ↗
  67. Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Jakob Prange, Austin Blodgett, Sarah Moeller, Aviram Stern, Adi Shalev, and Omri Abend. 2018. Comprehensive supersense disambiguation of English prepositions and possessives. In Proceedings of the 56th Annual Meeting of the Association for Computation… find
  68. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Sixth Message Understanding Conference (MUC-6): Proceedings of a Conference Held in Columbia, Maryland, November 6–8, 1995. https://doi.org/10.3115/1072399.1072405 ↗
  69. 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, pages 112–123, Denver, Colorado, USA. Association for Computational Ralph Weischedel, Martha Palmer, Mitchell Mar…

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/elazar-2022-text-based-np-enrichment/