Elamur Research⌕
☰
home / papers / 2016 / Idiom Token Classification using Sentential Distributed Semantics

Idiom Token Classification using Sentential Distributed Semantics

Summary

The paper addresses idiom token classification: deciding whether a given occurrence of a potentially idiomatic English phrase (e.g., break the ice) is meant literally or figuratively. Earlier systems typically depend on wide discourse context such as paragraphs, topic models, and lexical cohesion, and they usually build a separate model for each expression. The authors instead encode only the sentence containing the phrase, using Skip-Thought Vectors (Sent2Vec). This is a GRU-based encoder/decoder trained without supervision to predict neighbouring sentences, so its sentence vectors implicitly carry some contextual information. These vectors are fed to K-Nearest Neighbours and SVM classifiers and evaluated on the VNC-Tokens dataset. The baseline is the LDA topic-model approach of Peng et al. (2014). The sentence-only models are competitive with this paragraph-based baseline, and a single "general" classifier covering many expressions also turns out to be feasible. This matters for applications and under-resourced settings where reliable discourse context or per-idiom resources are unavailable.

Key points

  • Method: Sent2Vec (Kiros et al., 2015) sentence embeddings are combined with KNN and SVM classifiers, including linear and grid-searched SVM variants such as Linear-SVM-GE and Grid-SVM-GE.
  • Per-expression results: In the per-expression setting, the models beat the Peng et al. (2014) baseline on 3 of the 4 tested expressions. They also often achieve higher precision and/or recall.
  • Baseline comparison: The baseline could not be re-run because its modified Google stop list was unavailable. Comparisons therefore rely on the scores Peng et al. reported on the same data.
  • General classifier setup: The general classifier was trained on mixed expressions from the balanced part of VNC-Tokens, which covers 28 expressions. Results were averaged over 10 runs, with the real idiomatic-to-literal ratios preserved.
  • General classifier results: It outperformed the per-expression models on BlowWhistle but performed very poorly on SeeStar (F1 about 0.15–0.17).

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

Cited by

23 papers of our library cite it (of the 140673 whose bibliographies we read); 5 of them have a page here, 18 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/p16-1019

@inproceedings{salton2016idiom,
  title = {{Idiom Token Classification using Sentential Distributed Semantics}},
  author = {Salton, Giancarlo and Ross, Robert and Kelleher, John},
  booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2016},
  doi = {10.18653/v1/p16-1019},
  url = {https://doi.org/10.18653/v1/p16-1019}
}

References

26 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In ICLR. find our card
  2. David M. Blei, Andrew Y. Ng, and Michael I. Jordan. 2003. Latent dirichlet allocation. J. Mach. Learn. Res., 3:993–1022, March. find our card
  3. Linlin Li and Caroline Sporleder. 2010b. Using gaussian mixture models to detect figurative language in context. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, HLT ’10, pages 297–300, Stroudsburg, PA, USA. As… find
  4. Léon Bottou. 2010. Large-scale machine learning with stochastic gradient descent. In Proceedings of the 19th International Conference on Computational Statistics (COMPSTAT’2010), pages 177–187. find
  5. Lou Burnard. 2007. Reference guide for the british national corpus (xml edition). Technical report, http://www.natcorp.ox.ac.uk/. ↗
  6. Quinn McNemar. 1947. Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika, 12(2):153–157. find
  7. Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using rnn encoder–decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Langua… find
  8. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013a. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781. find
  9. Tomas Mikolov, Wen-tau Yih, and Geoffrey Zweig. 2013b. Linguistic regularities in continuous space word representations. In The 2013 Conference of the North Americal Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), pages 746–751. find
  10. Paul Cook, Afsaneh Fazly, and Suzanne Stevenson. 2008. The VNC-Tokens Dataset. In Proceedings of the LREC Workshop: Towards a Shared Task for Multiword Expressions (MWE 2008), Marrakech, Morocco. find
  11. Jing Peng, Anna Feldman, and Ekaterina Vylomova. 2014. Classifying idiomatic and literal expressions using topic models and intensity of emotions. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2019–2027, October. find
  12. Afsanesh Fazly, Paul Cook, and Suzanne Stevenson. 2009. Unsupervised type and token identification of idiomatic expressions. In Computational Linguistics, volume 35, pages 61–103. find our card
  13. Anna Feldman and Jing Peng. 2013. Automatic detection of idiomatic clauses. In Proceedings of the 14th International Conference on Computational Linguistics and Intelligent Text Processing - Volume Part I, CICLing’13, pages 435–446. find
  14. Giancarlo D. Salton, Robert J. Ross, and John D. Kelleher. 2014. An Empirical Study of the Impact of Idioms on Phrase Based Statistical Machine Translation of English to Brazilian-Portuguese. In Third Workshop on Hybrid Approaches to Translation (HyTra) at 14th Conference of the European Chapter of… find
  15. Chikara Hashimoto and Daisuke Kawahara. 2008. Construction of an idiom corpus and its application to idiom identification based on wsd incorporating idiom-specific features. In Proceedings of the conference on empirical methods in natural language processing, pages 992–1001. Association for Computat… find
  16. Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Y. Ng, and Christopher Potts. 2013. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 16… find
  17. Nal Kalchbrenner, Edward Grefenstette, and Phil Blunsom. 2014. A convolutional neural network for modelling sentences. June. find our card
  18. Yoon Kim. 2014. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25-29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL, pages 1746–1751. find our card
  19. Caroline Sporleder and Linlin Li. 2009. Unsupervised recognition of literal and non-literal use of idiomatic expressions. In Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics, pages 754–762. find our card
  20. Caroline Sporleder, Linlin Li, Philip Gorinski, and Xaver Koch. 2010. Idioms in context: The idix corpus. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC-2010), pages 639–646. find
  21. Ryan Kiros, Yukun Zhu, Ruslan R Salakhutdinov, Richard Zemel, Raquel Urtasun, Antonio Torralba, and Sanja Fidler. 2015. Skip-thought vectors. In Advances in Neural Information Processing Systems 28, pages 3276–3284. find
  22. Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger, editors, Advances in Neural Information Processing Systems 27, pages 3104–3112. find
  23. Linlin Li and Caroline Sporleder. 2010a. Linguistic cues for distinguishing literal and non-literal usages. In Proceedings of the 23rd International Conference on Computational Linguistics: Posters, pages 683– 691. find
  24. Vladimir N. Vapnik. 1995. The Nature of Statistical Learning Theory. Springer-Verlag New York, Inc., New York, NY, USA. find
  25. Aline Villavicencio, Francis Bond, Anna Korhonen, and Diana McCarthy. 2005. Editorial: Introduction to the special issue on multiword expressions: Having a crack at a hard nut. Comput. Speech Lang., 19(4):365–377. find
  26. Yukun Zhu, Ryan Kiros, Richard Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba, and Sanja Fidler. 2015. Aligning books and movies: Towards story-like visual explanations by watching movies and reading books. arXiv preprint arXiv:1506.06724. find our card

↑ back to top

This page in Markdown →