Elamur Research⌕
☰
home / papers / 2018 / Anaphora Resolution with the ARRAU Corpus

Anaphora Resolution with the ARRAU Corpus

Summary

Most coreference research relies on OntoNotes. That corpus skips expletives, singletons and many generic or abstract references, and it barely covers bridging or discourse deixis. This paper presents ARRAU, an English corpus with much broader anaphoric annotation, as the basis of the CRAC 2018 Shared Task, the first evaluation campaign built on ARRAU. In ARRAU, every NP is a markable, including non-referring ones, which are further labelled as expletive, predicative or quantificational. Mentions also carry morphosyntactic and semantic attributes, and minimal spans (MINs) are marked. The authors derived three datasets from Release 2: identity anaphora, bridging reference and discourse deixis. They also supplied evaluation scripts and baseline results. Running the untrained Stanford deterministic resolver on predicted markables produced a much lower CONLL score than the same system achieved at CoNLL 2011, and MIN information improved results by about five points. Because no other known resource supports all three tasks together, the datasets should make ARRAU more accessible and attract more research on less-studied anaphoric phenomena.

Key points

  • ARRAU has four sub-corpora: RST (413 Penn Treebank news documents, about 229K tokens), TRAINS dialogues, PEAR spoken narratives and GNOME. The shared task used RST, TRAINS and PEAR.
  • Release 2 was distributed through LDC in 2013 and contains about 350K words. It includes 5512 bridging references, of which 3777 in the RST part have typed relations (poss, subset, element, other, undersp-rel).
  • On predicted markables, the Stanford deterministic coreference resolver scored a CONLL score of 43.2, compared with 58.3 at CoNLL 2011. Adding MIN information raised it to roughly 48.9.
  • Markable extraction proved easier on ARRAU than mention extraction on OntoNotes, probably because ARRAU defines markables more loosely.
  • For bridging (Task 2), Roesiger (Stuttgart) built rule-based and ML-based systems. Their results were roughly in line with earlier ISNotes work on RST and TRAINS but weaker on PEAR.

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

Fields: Linguistics & languages

Topics: Coreference resolution

Cited by

39 papers of our library cite it (of the 140673 whose bibliographies we read); 20 of them have a page here, 19 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/w18-0702

@inproceedings{poesio2018anaphora,
  title = {{Anaphora Resolution with the ARRAU Corpus}},
  author = {Poesio, Massimo and Grishina, Yulia and Kolhatkar, Varada and Moosavi, Nafise and Roesiger, Ina and Roussel, Adam and Simonjetz, Fabian and Uma, Alexandra and Uryupina, Olga and Yu, Juntao and Zinsmeister, Heike},
  booktitle = {Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference},
  year = {2018},
  doi = {10.18653/v1/w18-0702},
  url = {https://doi.org/10.18653/v1/w18-0702}
}

References

47 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. M. P. Marcus, B. Santorini, and M. A. Marcinkiewicz. 1993. Building a large annotated corpus of english: the Penn Treebank. Computational Linguistics, 19(2):313–330. ↗ our card
  2. R. Artstein and M. Poesio. 2006. Identifying reference to abstract objects in dialogue. In Proc. of BRAN-DIAL, Potsdam. find
  3. K. Markert, Y. Hou, and M. Strube. 2012. Collective classification for fine-grained information status. In Proc. of the ACL, Jeju island, Korea. find our card
  4. D. Byron and J. Allen. 1998. Resolving demonstrative anaphora in the trains-93 corpus. In Proceedings of the Second Colloquium on Discourse, Anaphora and Reference Resolution. University of Lancaster. find
  5. N. N. Modjeska. 2003. Resolving other anaphors. Ph.D. thesis, University of Edinburgh. find
  6. L. Carlson, D. Marcu, and M. E. Okurowski. 2003. Building a discourse-tagged corpus in the framework of rhetorical structure theory. In J. Kuppevelt and R. Smith, editors, Current Directions in Discourse and Dialogue, pages 85–112. Kluwer. ↗ our card
  7. N. S. Moosavi and M. Strube. 2016. A proposal for a link-based entity aware metric. In Proc. of ACL, pages 632–642, Berlin. find
  8. H. H. Clark. 1975. Bridging. In Proceedings of TIN-LAP. find
  9. C. Müller and M. Strube. 2006. Multi-level annotation of linguistic data with MMAX2. In S. Braun, K. Kohn, and J. Mukherjee, editors, Corpus Technology and Language Pedagogy. New Resources, New Tools, New Methods, volume 3 of English Corpus Linguistics, pages 197–214. Peter Lang. find
  10. K. Clark and C. D. Manning. 2016. Improving coreference resolution by learning entity- level distributed representations. In Proc. of ACL, Berlin. find our card
  11. C. Navarretta. 2000. Abstract anaphora resolution in Danish. In Proc. of the 1st SIGdial Workshop on Discourse and Dialogue, pages 56–65. ACL. find our card
  12. W. L. Chafe. 1980. The Pear Stories: Cognitive, Cultural and Linguistic Aspects of Narrative Production. Ablex, Norwood, NJ. find
  13. S. Dipper and H. Zinsmeister. 2012. Annotating abstract anaphora. Language Resources and Evaluation, 46(1):37–52. ↗
  14. M. Palmer, D. Gildea, and Kingsbury. 2005. The proposition bank: A corpus annotated with semantic roles. Computational Linguistics, 31(1):71–106. find
  15. J. A. Hawkins. 1978. Definiteness and Indefiniteness. Croom Helm, London. find
  16. M. Poesio. 2000a. Annotating a corpus to develop and evaluate discourse entity realization algorithms: issues and preliminary results. In Proc. of LREC, pages 211–218, Athens. find
  17. Y. Hou, K. Markert, and M. Strube. 2013. Global inference for bridging anaphora resolution. In Proc. of the NAACL, pages 907–917, Atlanta, Georgia. find our card
  18. M. Poesio. 2000b. The GNOME Annotation Scheme Manual, fourth version edition. University of Edinburgh, HCRC and Informatics, Scotland. Available from http://cswww.essex.ac.uk/Research/nle/ corpora/GNOME/anno_manual_4.htm. ↗
  19. V. Kolhatkar. 2014. Resolving Shell Nouns. Ph.D. thesis, University of Toronto. find
  20. V. Kolhatkar and G. Hirst. 2014. Resolving shell nouns. In Proc. of EMNLP, pages 499–510, Doha, Qatar. find
  21. M. Poesio. 2004a. Discourse annotation and semantic annotation in the GNOME corpus. In Proceedings of the ACL Workshop on Discourse Annotation, pages 72–79, Barcelona. find
  22. V. Kolhatkar, H. Zinsmeister, and G. Hirst. 2013. Interpreting anaphoric shell nouns using antecedents of cataphoric shell nouns as training data. In Proc. of EMNLP, Seattle. G. find our card
  23. M. Poesio. 2004b. The MATE/GNOME scheme for anaphoric annotation, revisited. In Proceedings of SIGDIAL, Boston. find our card
  24. Lample, M. Ballesteros, S. Subramanian, K. Kawakami, and C. Dyer. 2016. Neural architectures for named entity recognition. In Proceedings of NAACL, pages 260–270. Association for Computational Linguistics. ↗
  25. M. Poesio and R. Artstein. 2005a. Annotating (anaphoric) ambiguity. In Proceedings of the Corpus Linguistics Conference, Birmingham. find
  26. H. Lee, A. Chang, Y. Peirsman, N. Chambers, M. Surdeanu, and D. Jurafsky. 2013. Deterministic coreference resolution based on entity-centric, precision-ranked rules. Computational Linguistics, 39(4):885–916. ↗ our card
  27. M. Poesio and R. Artstein. 2005b. The reliability of anaphoric annotation, reconsidered: Taking ambiguity into account. In Proceedings of ACL Workshop on Frontiers in Corpus Annotation, pages 76–83. find our card
  28. A. Marasović, L. Born, J. Opitz, and A. Frank. 2017. A mention-ranking model for abstract anaphora resolution. In Proc. of EMNLP, pages 221–232, Copenhagen. find our card
  29. M. Poesio and R. Artstein. 2008. Anaphoric annotation in the ARRAU corpus. In Proc. of LREC, Marrakesh. O. Uryupina, R. Artstein, A. Bristot, F. Cavicchio, F. Delogu, K. Rodriguez, and M. Poesio. In press. Annotating a broad range of anaphoric phenomena, in a variety of genres: the arrau corpus. Journal of Natural Language Engineering. find our card
  30. M. Poesio, A. Patel, and B. Di Eugenio. 2006. Discourse structure and anaphora in tutorial dialogues: an empirical analysis of two theories of the global focus. Research in Language and Computation, 4:229–257. Special Issue on Generation and Dialogue. ↗
  31. O. Uryupina and M. Poesio. 2012. Domain-specific vs. uniform modeling for coreference resolution. In Proc. of LREC, pages 187–191, Istanbul. ELRA. find our card
  32. M. Poesio, S. Pradhan, M. Recasens, K. Rodriguez, and Y. Versley. 2016. Annotated corpora and annotation tools. In M. Poesio, R. Stuckardt, and Y. Versley, editors, Anaphora Resolution: Algorithms, Resources and Applications, chapter 4. Springer. ↗
  33. O. Uryupina and M. Poesio. 2013. Evalita 2011: Anaphora resolution task. In Evaluation of Natural Language and Speech Tools for Italian, number 7689 in Lecture Notes in Computer Science, pages 146–155. Springer. find
  34. M. Poesio, R. Stevenson, B. Di Eugenio, and J. M. Hitzeman. 2004. Centering: A parametric theory and its instantiations. Computational Linguistics, 30(3):309–363. ↗
  35. Y. Versley, S. Ponzetto, M. Poesio, V. Eidelman, A. Jern, J. Smith, X. Yang, and A. Moschitti. 2008. Bart: A modular toolkit for coreference resolution. In Proc. of ACL, demo session, Columbus, OH. find our card
  36. M. Poesio and R. Vieira. 1998. A corpus-based investigation of definite description use. Computational Linguistics, 24(2):183–216. ↗
  37. R. Vieira. 1998. Definite Description Resolution in Unrestricted Texts. Ph.D. thesis, University of Edinburgh, Centre for Cognitive Science. find
  38. S. Pradhan, X. Luo, M. Recasens, E. Hovy, V. Ng, and M. Strube. 2014. Scoring coreference partitions of predicted mentions: A reference implementation. In Proc. of the ACL, pages 30–35, Baltimore. find our card
  39. B. L. Webber. 1991. Structure and ostension in the interpretation of discourse deixis. Language and Cognitive Processes, 6(2):107–135. ↗
  40. S. S. Pradhan, E. Hovy, M. Marcus, M. Palmer, L. Ramshaw, and R. Weischedel. 2007a. Ontonotes: A unified relational semantic representation. International Journal on Semantic Computing, 1(4):405– 419. ↗
  41. S. J. Wiseman, A. M. Rush, S. M. Shieber, and J. Weston. 2015. Learning anaphoricity and antecedent ranking features for coreference resolution. In Proc. of the ACL, Bejing. find our card
  42. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. Conll-2012 shared task: Modeling multilingual unrestricted coreference in ontonotes. In Joint Conference on EMNLP and CoNLL - Shared Task, pages 1–40, Jeju Island, Korea. Association for Computational Linguistics. find our card
  43. Sameer Pradhan, Lance Ramshaw, Ralph Weischedel, Jessica MacBride, and Linnea Micciulla. 2007b. Unrestricted Coreference: Indentifying Entities and Events in OntoNotes. In in Proceedings of the IEEE International Conference on Semantic Computing (ICSC). find
  44. M. Recasens, L. Màrquez, E. Sapena, M. A. Martı́, M. Taulé, V. Hoste, M. Poesio, and Y. Versley. 2010. Semeval-2010 task 1: Coreference resolution in multiple languages. In Proc. SEMEVAL 2010, Uppsala. find our card
  45. K. Rodriguez. 2010. Resources for linguistically motivated multilingual anaphora resolution. Ph.D. thesis, Universitá di Trento. ↗
  46. I. Roesiger. 2018. Rule- and learning-based methods for bridging resolution in the ARRAU corpus. In Proc. of CRAC. find our card
  47. W. M. Soon, D. C. Y. Lim, and H. T. Ng. 2001. A machine learning approach to coreference resolution of noun phrases. Computational Linguistics, 27(4). ↗ our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/poesio-2018-anaphora-resolution-arrau-corpus/