NoEl: An Annotated Corpus for Noun Ellipsis in English
What it is about
The authors annotate the first 100 movies of the Cornell Movie Dialogs corpus, about 672,000 tokens, for noun ellipsis: a licensor (a cardinal, ordinal, possessive, determiner, quantifier or adjective) whose head noun is left out. The corpus has 946 instances, 438 with a textual antecedent and 508 exophoric, which is about 14 per 10,000 tokens, much higher than the rate reported for written VPE corpora. The annotation is standoff, with three annotators and Fleiss' kappa between 0.85 and 0.92. Baseline classifiers on trigram POS and word-embedding features detect licensors with F1 up to about 0.73 (linear SVM), and a random forest resolves the antecedent with F1 about 0.75. Cardinal licensors often have a cardinal modifier in the antecedent (38% of the time), a parallelism the authors suggest as a resolution cue.
Ideas
- I1.
en/seeds/nominal: rules that flag a determiner, cardinal or possessive without an overt noun head (for example adet,nummodornmod:possnode whose head is not a noun), with precision and recall on NoEl under the paper's 80/20 split. The paper is CC BY-NC (ELRA); the NoEl data has its own licence, to be checked before test use. - I2.
prag/world: the parallel-tag cue (licensor tag equal to the antecedent modifier tag) as a filter on candidate antecedents, measured on the 438 endophoric cases. - I3. Compare the paper's trigram classifier with a detector built from
entrees (a missing-head rule plus the licensor class), using cross-validation on NoEl. - I4. Use the 508 exophoric instances as negatives for the ellipsis rules, and measure the false-positive rate on idiomatic cardinals such as "five minutes".
For Mova
The ideas touch en/seeds/nominal, en/src/ud.rs and prag. The relevant chapters are 29. Ellipsis, word order and information structure, 12-pronouns-determiners-numerals.md (licensors) and 22-phrases.md. Until the licence is confirmed, NoEl is used for measurement only.
Cite
@inproceedings{khullar2020noel,
title = {{NoEl: An Annotated Corpus for Noun Ellipsis in English}},
author = {Khullar, Payal and Majmundar, Kushal and Shrivastava, Manish},
booktitle = {Proceedings of the Twelfth Language Resources and Evaluation Conference},
year = {2020},
url = {https://aclanthology.org/2020.lrec-1.5/}
}References
- Agel, V. (1991). Lexikalische ellipsen fragen und vorschläge. Zeitschrift für Germanistische Linguistik, 19. find
- Asao, Y., Iida, R., and Torisawa, K. (2018). Annotating zero anaphora for question answering. In LREC. find
- Bos, J. and Spenader, J. (2011). An annotated corpus for the analysis of vp ellipsis. Language Resources and Evaluation, 45(4):463â494. find
- Chen, W. (2016). The motivation of ellipsis. Theory and Practice in Language Studies, 6(11):2134–2139. find
- Chung, S., Ladusaw, W., and McCloskey, J. (2010). Sluicing (:) between structure and inference. In Representing language: Essays in honor of Judith Aissen. find
- Dalrymple, M., Shieber, S. M., and Pereira, F. C. N. (1991). Ellipsis and higher-order unification. Linguistics and Philosophy, 14(4):399–452. find
- Danescu-Niculescu-Mizil, C. and Lee, L. (2011). Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, ACL 2011. find
- Dean, K. K., Cheung, J. C. K., and Precup, D. (2016). Verb phrase ellipsis resolution using discriminative and margin-infused algorithms. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, page 1734â1743. find our card
- Frazier, L. (2008). Processing ellipsis: A processing solution to the undergeneration problem? In Proceedings of the 26th West Coast Conference on Formal Linguistics. find
- Gardiner, M. (2003). Identifying and resolving one-anaphora. Department of Computing, Division of ICS, Macquarie University. find
- Goksun, T., Roeper, T. W., Hirsh-Pasek, K., and Golinkoff, R. M. (2010). From nounphrase ellipsis to verbphrase ellipsis: The acquisition path from context to abstract reconstruction. find
- Gunther, C. (2011). Noun ellipsis in english: adjectival modifiers and the role of context. The structure of the noun phrase in English: synchronic and diachronic explorations, 15(2):279–301. find
- Halliday, M. A. K. and Hasan, R. (1976). Cohesion in english. page 76. find
- Hansen, V. P. B. and Sogaard, A. (2019). What do you mean âwhy?â: Resolving sluices in conversations. find
- Hardt, D. (1992). An algorithm for vp ellipsis. page 9â14. find
- Hardt, D. (1998). Improving ellipsis resolution with transformation-based learning. 1998. find
- Hardt, D. (1999). Dynamic interpretation of verb phrase ellipsis. Linguistics and Philosophy, 22(2):187–221. find
- Hobbs, J. R. and Kehler, A. (1997). A theory of parallelism and the case of vp ellipsis. In Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics, ACL ’98/EACL ’98, pages 394–401, Stroudsburg, PA, USA. Association for Computational Linguistics. find
- Hyams, N., Mateu, V., and Winans, L. (2017). Ellipsis meets wh-movement: sluicing in early grammar. find
- Iida, R., Inui, K., and Matsumoto, Y. (2007). Zero-anaphora resolution by learning rich syntactic pattern features. ACM Trans. Asian Lang. Inf. Process., 6, 12. find
- Johnson, K. (2001). What vp ellipsis can do, and what it canât, but not why. pages 439–479. find
- Khullar, P., Anthony, A., and Shrivastava, M. (2019). Using syntax to resolve npe in english. In Proceedings of Recent Advances in Natural Language Processing, pages 535–541. find our card
- Kim, N., Brehm, L., and Yoshida, M. (2019). The online processing of noun phrase ellipsis and mechanisms of antecedent retrieval. Language, Cognition and Neuroscience, 34(2):190–213. find
- Langacker, R. W. (1999). Grammar and Conceptualization (Cognitive Linguistics Research), volume 14. Mouton de Gruyter, New York. find
- Lappin, S. (1996). The interpretatin of ellipsis. In Shalom Lappin, editor, The Handbook of Contemporary Semantic Theory, pages 145–176. Blackwell. find
- Lapshinova-Koltunski, E., Hardmeier, C., and Krielke, P. (2018). Parcorfull: a parallel corpus annotated with full coreference. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation, LREC 2018, Miyazaki, Japan, May 7-12, 2018. find
- Lindenbergh, C., van Hout, A., and Hollebrandse, B. (2015). Extending ellipsis research: The acquisition of sluicing in dutch. BUCLD 39 Online Proceedings Supplement, 39. find
- Lobeck, A. (1995). Functional Heads, Licensing, and Identification. Oxford University Press. find
- Marcus, M., Kim, G., Marcinkiewicz, M. A., MacIntyre, R., Bies, A., Ferguson, M., Katz, K., and Schasberger, B. (1994). The penn treebank: Annotating predicate argument structure. In Proceedings of the Workshop on Human Language Technology, HLT ’94, pages 114–119, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
- McShane, M. and Babkin, P. (2016). Detection and resolution of verb phrase ellipsis. Linguistic Issues in Language Technology, 13(1). find our card
- McShane, M., Nirenburg, S., and Babkin, P. (2015). Sentence trimming in service of verb phrase ellipsis resolution. In EAPCogSci. find
- Menzel, K. and Lapshinova-Koltunski, E. (2014). Kontrastive analyse deutscher und englischer kohäsionsmittel in verschiedenen diskurstypen. tekst i dyskurs - Text und Diskurs. Zeitschrift der Abteilung für germanistische Sprachwissenschaft des Germanistischen Instituts Warschau. find
- Menzel, K. (2017). Understanding English-German contrasts: a corpus-based comparative analysis of ellipses as cohesive devices. Ph.D. thesis, Universitat des Saar-¨ landes, Saarbrucken. find
- Merchant, J. (2004). Fragments and ellipsis. Linguistics and Philosophy, 27(6):661–738. find
- Merchant, J. (2010). Three Kinds of Ellipsis: Syntactic, Semantic, Pragmatic? find
- Nielsen, L. A. (2003). Using machine learning techniques for vpe detection. 1. find
- Nielsen, L. A. (2004). Verb phrase ellipsis detection using automatically parsed text. 01. find our card
- Nielsen, L. A. (2005). A corpus-based study of verb phrase ellipsis identification and resolution. Kingâs College London. find
- Oh, S.-Y. (2005). English zero anaphora as an interactional resource. Research on Language and Social Interaction, 38(3):267–302. find
- Park, D. (2017). When does ellipsis occur, and what is elided? PhD dissertation, University of Maryland. find
- Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830. find
- Recasens, M., Hu, Z., and Rhinehart, O. (2016). Sense anaphoric pronouns: Am i one? pages 1–6, 01. find
- Rouveret, A. (2012). Vp ellipsis, phases and the syntax of morphology. Natural Language & Linguistic Theory, 30(3):897â963. find
- Schuster, S., Nivre, J., and Manning, C. D. (2018). Sentences with gapping: Parsing and reconstructing elided predicates. ArXiv e-prints. find our card
- Silveira, N., Dozat, T., de Marneffe, M.-C., Bowman, S., Connor, M., Bauer, J., and Manning, C. D. (2014). A gold standard dependency corpus for English. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC-2014). find
- Stenetorp, P., Pyysalo, S., Topić, G., Ohta, T., Ananiadou, S., and Tsujii, J. (2012). Brat: A web-based tool for nlp-assisted text annotation. In Proceedings of the Demonstrations at the 13th Conference of the European Chapter of the Association for Computational Linguistics, EACL ’12, pages 102–107, Stroudsburg, PA, USA. Association for Computational Linguistics. find
- van Craenenbroeck, J. and Merchant, J. (2013). Ellipsis phenomena. In The Cambridge Handbook of Generative Syntax, pages 701–745. Cambridge University Press. find
- Wijnen, F., Roeper, T. W., and van der Meulen, H. (2003). Discourse binding: Does it begin with nominal ellipsis? find
- Xiang, M., Grove, J., and Merchant, J. (2014). Ellipsis sites induce structural priming effects. find
- Yeh, C.-L. and Chen, Y.-C. (2019a). Using zero anaphora resolution to improve text categorization. 03. find
- Yeh, C.-L. and Chen, Y.-J. (2019b). An empirical study of zero anaphora resolution in chinese based on centering model. 03. find
- Zhang, W.-N., Zhang, Y., Liu, Y., Di, D., and Liu1, T. (2019). A neural network approach to verb phrase ellipsis resolution. find
- Zhao, G. (2015). The motivation of ellipsis. Theory and Practice in Language Studies, 5(6):1275–1279, June. find
This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/gram-2020-khullar-noel-annotated-corpus-noun-ellipsis/