Abstract
Coordinations refer to phrases such as “A and/but/or/... B”. The detection of coordinations remains a major problem due to the complexity of their components. Existing work normally classified the training data into two categories: correct and incorrect. This often caused the problem of data imbalance which inevitably damaged performances of the models they used. We propose to fully exploit the differences between training data by formulating the detection of coordinations as a ranking problem to remedy this problem. We develop a novel model based on the long short-term memory network. Experiments on Penn Treebank and Genia verified the effectiveness of the proposed model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Other neural network models can also be employed to learn representations. Here we choose this one for its effectiveness and simplicity.
- 2.
“&” which is usually regarded as a special form of “and” is excluded for it only appears in proper nouns and constitutes simple coordinations that are easy to identify.
- 3.
- 4.
In Genia, the proportion is even higher.
References
Bikel, D.M.: Intricacies of collins’ parsing model. Comput. Linguist. 30(4), 479–511 (2004)
Buyko, E., Hahn, U.: Are morpho-syntactic features more predictive for the resolution of noun phrase coordination ambiguity than Lexico-semantic similarity scores? In: COLING, vol. 1, pp. 89–96. ACL (2008)
Buyko, E., Tomanek, K., Hahn, U.: Resolution of coordination ellipses in biological named entities using conditional random fields. In: PACLING, pp. 163–171 (2007)
Chantree, F., Kilgarriff, A., De Roeck, A., Willis, A.: Disambiguating coordinations using word distribution information. In: Proceedings of RANLP 2005 (2005)
Elman, J.L.: Distributed representations, simple recurrent networks, and grammatical structure. Mach. Learn. 7(2–3), 195–225 (1991)
Hanamoto, A., Matsuzaki, T., Tsujii, J.: Coordination structure analysis using dual decomposition. In: EACL, pp. 430–438. ACL (2012)
Hara, K., Shimbo, M., Okuma, H., Matsumoto, Y.: Coordinate structure analysis with global structural constraints and alignment-based local features. In: ACL-AFNLP, vol. 2, pp. 967–975. ACL (2009)
Hogan, D.: Coordinate Noun Phrase Disambiguation in a Generative Parsing Model. ACL (2007)
Kawahara, D., Kurohashi, S.: Generative modeling of coordination by factoring parallelism and selectional preferences. In: IJCNLP, pp. 456–464 (2011)
Kim, J.D., Ohta, T., Tateisi, Y., Tsujii, J.: Genia corpurs-semantically annotated corpus for bio-textmining. Bioinformatics 19(suppl 1), i180–i182 (2003)
Kurohashi, S., Nagao, M.: A syntactic analysis method of long Japanese sentences based on the detection of conjunctive structures. Comput. Linguist. 20(4), 507–534 (1994)
Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. arXiv preprint arXiv:1405.4053 (2014)
Li, J., Luong, M.T., Jurafsky, D., Hovy, E.: When are tree structures necessary for deep learning of representations? arXiv preprint arXiv:1503.00185 (2015)
Li, J., Monroe, W., Jurafsky, D.: A simple, fast diverse decoding algorithm for neural generation. arXiv preprint arXiv:1611.08562 (2016)
Li, J., Monroe, W., Shi, T., Ritter, A., Jurafsky, D.: Adversarial learning for neural dialogue generation. arXiv preprint arXiv:1701.06547 (2017)
Lopyrev, K.: Learning distributed representations of phrases (2014)
Marcus, M.P., Marcinkiewicz, M.A., Santorini, B.: Building a large annotated corpus of English: the penn treebank. Comput. Linguist. 19(2), 313–330 (1993)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS, pp. 3111–3119 (2013)
Mitchell, J., Lapata, M.: Composition in distributional models of semantics. Cogn. Sci. 34(8), 1388–1429 (2010)
Miyao, Y., Tsujii, J.: Deep linguistic analysis for the accurate identification of predicate-argument relations. In: COLING, p. 1392. ACL (2004)
Nakov, P., Hearst, M.: Using the web as an implicit training set: application to structural ambiguity resolution. In: HLT-EMNLP, pp. 835–842. ACL (2005)
Nyblom, J., Kohonen, S., Haverinen, K., Salakoski, T., Ginter, F.: Predicting conjunct propagation and other extended stanford dependencies. In: Proceedings of the International Conference on Dependency Linguistics (Depling 2013), pp. 252–261 (2013)
Okumura, A., Muraki, K.: Symmetric pattern matching analysis for English coordinate structures. In: ANLP, pp. 41–46. ACL (1994)
Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. EMNLP 14, 1532–1543 (2014)
Schachter, P.: Constraints on coördination. Language, pp. 86–103 (1977)
Schmidhuber, J., Gers, F.A., Eck, D.: Learning nonregular languages: a comparison of simple recurrent networks and LSTM. Neural Comput. 14(9), 2039–2041 (2002)
Shimbo, M., Hara, K.: A discriminative learning model for coordinate conjunctions. In: EMNLP-CoNLL, pp. 610–619. ACL (2007)
Sundermeyer, M., Schlüter, R., Ney, H.: LSTM neural networks for language modeling. In: INTERSPEECH, pp. 194–197 (2012)
Wang, X., Sudoh, K., Nagata, M.: Empty category detection with joint context-label embeddings. In: HLT-NAACL, pp. 263–271 (2015)
Wang, X., Sudoh, K., Nagata, M.: Enhanced word embeddings from a hierarchical neural language model. In: CIKM, pp. 1927–1930. ACM (2015)
Weston, J., Bengio, S., Usunier, N.: WSABIE: scaling up to large vocabulary image annotation. IJCAI 11, 2764–2770 (2011)
Yoshimoto, A., Hara, K., Shimbo, M., Matsumoto, Y.: Coordination-aware dependency parsing (preliminary report). IWPT 2015, 66 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, X., Li, R., Shindo, H., Sudoh, K., Nagata, M. (2018). Learning to Rank for Coordination Detection. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2017. Lecture Notes in Computer Science(), vol 10761. Springer, Cham. https://doi.org/10.1007/978-3-319-77113-7_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-77113-7_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-77112-0
Online ISBN: 978-3-319-77113-7
eBook Packages: Computer ScienceComputer Science (R0)