Bridging resolution: Task definition, corpus resources and rule-based experiments

What it is about

Bridging anaphors are new referents that are interpreted through an earlier, non-identical one («The city is planning a new town hall and the construction will start next week» — the construction of the town hall). The paper re-implements the rule-based resolver of Hou et al. 2014 (eight rules applied in order of precision: building parts, relatives, heads of state of a country, job titles of an organisation, percentages, one/indefinite pronouns of a plural set, argument-taking nouns, and general semantic connectivity from N prep N counts in a large corpus) and adds a part–whole rule for unmodified the N. On ISNotes it reaches 50.0 precision, 12.8 recall for full resolution; filtering out anaphors already linked by coreference raises precision from 32 to 48–50 with predicted or gold coreference alike. On ARRAU it collapses (F1 0.3) and on scientific text too, which the authors trace to two different things called bridging: referential bridging (context-dependent, mostly short definites) and lexical bridging (any part–whole or subset relation between words, e.g. Europe – Spain, often not anaphoric at all). Subset and aggregation cases («a pug and a terrier … the dogs») are closer to coreference.

Ideas

• I1. Add a bridging pass after coreference in coref/src/sieve.rs, with high-precision rules from the paper's list, only for mentions the sieves left unlinked and only for unmodified definites (the N): building part → the latest building (house, castle, hut … the door, the roof, the window), body part → the latest animate, relative noun (husband, mother, son) → the latest person, one/another/the other → the latest plural set. Output as a separate bridging link with its rule id (CorefUD has Bridge=; coref resolve now drops it). Measure on GUM dev bridging links (precision first) and whether removing these anaphors from the exact/strict sieves raises their precision (error type 2 «part versus whole» in coref — SLM coreference: a sieve of rules with a reason for every link).
• I2. Compute the paper's two corpus statistics from Mova's own parsed tales instead of GigaWord: semantic connectivity (count of N1 of/in/on N2 pairs, e.g. door of the house) and the argument-taking ratio of a noun (share of its occurrences with an nmod/possessive). Both are deterministic counts, licence-clean if built from the commercial-licence corpora; store them as a small TSV and use them as the backstop rule.
• I3. Fill the implicit argument in frames: «He came to a house. The door was open.» → the door's frame gets of=house. Then «Where was the open door?» or «What was open?» can be answered with the house. Implement in prag/src/frames.rs (an obls entry of=), driven by the same rules; measure on course questions that ask about a part of an earlier object.
• I4. Keep referential and lexical bridging apart in Mova's docs and data: only referential bridging should create links; lexical part–whole between names (Senegal – Southern Senegal) is a reason to block coreference, which is how it helps the sieve.

For Mova

35. Reference and coreference §3.2 (bridging) and §9 (the coref crate). Code: coref/src/sieve.rs (bridging pass, blocking), coref/src/corefud.rs (keep Bridge for scoring), prag/src/frames.rs (implicit of= argument). Measures: bridging precision on GUM dev, exact/strict_a precision, CoNLL F1 without singletons; GUM and ISNotes/ARRAU are for tests only.

Topics: Coreference resolution

Cite

The paper itself, not this card. BibTeX from the library's record of the work.

@inproceedings{roesiger2018bridging,
  title = {{Bridging resolution: Task definition, corpus resources and rule-based experiments}},
  author = {Roesiger, Ina and Riester, Arndt and Kuhn, Jonas},
  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics},
  year = {2018},
  url = {https://aclanthology.org/C18-1298/}
}

References

45 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Nicholas Asher and Alex Lascarides. 1998. Bridging. Journal of Semantics, 15(1):83–113. find
2. Regina Barzilay and Mirella Lapata. 2008. Modeling local coherence: An entity-based approach. Computational Linguistics, 34(1):1–34. ↗
3. Stefan Baumann and Arndt Riester. 2012. Referential and Lexical Givenness: semantic, prosodic and cognitive aspects. In Gorka Elordieta and Pilar Prieto, editors, Prosody and Meaning, number 25 in Interface Explorations. Mouton de Gruyter, Berlin. ↗
4. Anders Björkelund and Jonas Kuhn. 2014. Learning structured perceptrons for coreference resolution with latent antecedents and non-local features. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 47–57, Baltimore, Maryland, June. Association for Computational Linguistics. find
5. Aoife Cahill and Arndt Riester. 2012. Automatically acquiring fine-grained information status distinctions in German. In Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 232–236. Association for Computational Linguistics. find
6. Herbert H. Clark. 1975. Bridging. In Proceedings of the 1975 workshop on Theoretical issues in natural language processing, pages 169–174. Association for Computational Linguistics. find
7. Kari Fraurud. 1990. Definiteness and the processing of noun phrases in natural discourse. Journal of Semantics, 7(4):395–433. ↗
8. Claire Gardent, Hélène Manuélian, and Eric Kow. 2003. Which bridges for bridging definite descriptions? In Proceedings of EACL: Fourth International Workshop on Linguistically Interpreted Corpora, pages 69–76, Budapest. find
9. Yulia Grishina. 2016. Experiments on bridging across languages and genres. In CORBON@ HLT-NAACL, pages 7–15. find
10. John A Hawkins. 1978. Definiteness and indefiniteness: A study in reference and grammaticality prediction. atlantic highlands. find
11. Marti A. Hearst. 1994. Multi-paragraph segmentation of expository text. In Proceedings of the 32nd Annual Meeting of the Association for Computational Linguistics, pages 9–16. find
12. Jerry R Hobbs, Mark E Stickel, Douglas E Appelt, and Paul Martin. 1993. Interpretation as abduction. Artificial Intelligence, 63:69–142. find
13. Yufang Hou, Katja Markert, and Michael Strube. 2013a. Cascading collective classification for bridging anaphora recognition using a rich linguistic feature set. In EMNLP, pages 814–820. find
14. Yufang Hou, Katja Markert, and Michael Strube. 2013b. Global inference for bridging anaphora resolution. In Proceedings of NAACL-HLT, pages 907–917. find our card
15. 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 EMNLP, pages 2082–2093. find
16. Yufang Hou. 2016a. Incremental fine-grained information status classification using attention-based lstms. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1880–1890. find
17. Yufang Hou. 2016b. Unrestricted Bridging Resolution. Ph.D. thesis. find our card
18. Saul Kripke. 1972. Naming and necessity. In Donald Davidson and Gilbert Harman, editors, Semantics of Natural Language, pages 253–355. Springer, Dordrecht. ↗
19. Emmanuel Lassalle and Pascal Denis. 2011. Leveraging different meronym discovery methods for bridging resolution in french. Anaphora Processing and Applications, pages 35–46. find
20. Sebastian Löbner. 1998. Definite associative anaphora. manuscript) http://user.phil-fak. uniduesseldorf. de/˜ loebner/publ/DAA-03. pdf. ↗
21. 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: Long Papers-Volume 1, pages 795–804. Association for Computational Linguistics. find
22. Anna Nedoluzhko, Jiřı́ Mı́rovskỳ, Radek Ocelák, and Jiřı́ Pergler. 2009. Extended coreferential relations and bridging anaphora in the prague dependency treebank. In Proceedings of the 7th Discourse Anaphora and Anaphor Resolution Colloquium (DAARC 2009), Goa, India, pages 1–16. find
23. Malvina Nissim, Shipra Dingare, Jean Carletta, and Mark Steedman. 2004. An annotation scheme for information status in dialogue. LREC 2004. find
24. Massimo Poesio and Ron Artstein. 2008. Anaphoric Annotation in the ARRAU Corpus. In International Conference on Language Resources and Evaluation (LREC), Marrakech, Morocco, May. find
25. Massimo Poesio and Renata Vieira. 1998. A corpus-based investigation of definite description use. Computational linguistics, 24(2):183–216. ↗
26. Massimo Poesio, Renata Vieira, and Simone Teufel. 1997. Resolving bridging references in unrestricted text. In Proceedings of a Workshop on Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Texts, pages 1–6. Association for Computational Linguistics. find
27. Massimo Poesio, Rahul Mehta, Axel Maroudas, and Janet Hitzeman. 2004. Learning to resolve bridging references. In Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics, page 143. Association for Computational Linguistics. find
28. Ellen F. Prince. 1981. Toward a taxonomy of given-new information. In Radical Pragmatics, pages 223–55. Academic Press. find
29. Altaf Rahman and Vincent Ng. 2012. Learning the fine-grained information status of discourse entities. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, EACL ’12, pages 798–807, Stroudsburg, PA, USA. Association for Computational Linguistics. find
30. Marta Recasens and Eduard Hovy. 2010. A typology of near-identity relations for coreference (nident). In LREC. find
31. Marta Recasens, Maria Antonia Marti, and Constantin Orasan. 2012. Annotating near-identity from coreference disagreements. In LREC, pages 165–172. find
32. Arndt Riester and Stefan Baumann. 2017. The RefLex Scheme – Annotation guidelines. SinSpeC. Working papers of the SFB 732 Vol. 14, University of Stuttgart. ↗
33. Arndt Riester and Jörn Piontek. 2015. Anarchy in the NP. When new nouns get deaccented and given nouns dont. Lingua, 165(B):230–253. find
34. Anna Roitberg and Anna Nedoluzhko. 2016. Bridging corpus for russian in comparison with czech. In COR-BON@ HLT-NAACL, pages 59–66. find
35. Mats Rooth. 1992. A theory of focus interpretation. Natural Language Semantics, 1(1):75–116. ↗
36. Ina Rösiger, Maximilian Köper, Kim Anh Nguyen, and Sabine Schulte im Walde. 2018. Integrating predictions from neural-network relation classifiers into coreference and bridging resolution. In Proceedings of NAACL-HLT: Workshop on Computational Models of Reference, Anaphora and Coreference, New Orleans, USA, June. find
37. Ina Rösiger. 2016. Scicorp: A corpus of english scientific articles annotated for information status analysis. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016). find our card
38. 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). find
39. Ina Rösiger. 2018b. Rule- and learning-based methods for bridging resolution in the arrau corpus. In Proceedings of NAACL-HLT: Workshop on Computational Models of Reference, Anaphora and Coreference, New Orleans, USA, June. find
40. Vered Shwartz and Ido Dagan. 2016. Path-based vs. distributional information in recognizing lexical semantic relations. arXiv preprint arXiv:1608.05014. ↗
41. Sidney Siegel and N. John Jr. Castellan. 1988. Nonparametric Statistics for the Behavioral Sciences. McGraw-Hill, Berkeley, CA, 2nd edition. find
42. Robert Speer, Joshua Chin, and Catherine Havasi. 2017. Conceptnet 5.5: An open multilingual graph of general knowledge. In AAAI. Olga Uryupina, Ron Artstein, Antonella Bristot, Ferederica Cavicchio, Francesca Delogu, Kepa Rodriguez, and Massimo Poesio. to appear. Annotating a broad range of anaphoric phenomena, in a variety of genres: the arrau corpus. Journal of Natural Language Engineering. find
43. Renata Vieira and Simone Teufel. 1997. Towards resolution of bridging descriptions. In Proceedings of the eighth conference on European chapter of the Association for Computational Linguistics, pages 522–524. Association for Computational Linguistics. find
44. Amir Zeldes. 2017. The gum corpus: creating multilayer resources in the classroom. Language Resources and Evaluation, 51(3):581–612, Sep. ↗
45. Šárka Zikánová, Eva Hajicová, Barbora Hladká, Pavlı́na Jı́nová, Jirı́ Mı́rovskỳ, Anja Nedoluzhko, Lucie Poláková, Katerina Rysová, Magdaléna Rysová, and Jan Václ. 2015. Discourse and coherence. From the Sentence Structure to Relations in Text. Institute of Formal and Applied Linguistics. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/roesiger-2018-bridging-resolution-task-definition-corpus/