emnlp emnlp2013 emnlp2013-59 emnlp2013-59-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Joo-Kyung Kim ; Marie-Catherine de Marneffe
Abstract: Continuous space word representations extracted from neural network language models have been used effectively for natural language processing, but until recently it was not clear whether the spatial relationships of such representations were interpretable. Mikolov et al. (2013) show that these representations do capture syntactic and semantic regularities. Here, we push the interpretation of continuous space word representations further by demonstrating that vector offsets can be used to derive adjectival scales (e.g., okay < good < excellent). We evaluate the scales on the indirect answers to yes/no questions corpus (de Marneffe et al., 2010). We obtain 72.8% accuracy, which outperforms previous results (∼60%) on tichihs corpus aornmd highlights sth rees quality o6f0% the) scales extracted, providing further support that the continuous space word representations are meaningful.
semi-supervised learning. In Proceedings of the 48th YRorCnsgchaeulintrgcCesBhtoiwu,mael3nr :1gdbkJfieaosnrl3,t.wv7R–ianT1te´h.jdu5mar2Jnlu0o.s Dt3arin.cWgsuhlkAaeromftn eMrpu,.aiPoc2nlhg0sep.i8raoIlnbLAgVPe:iraunoldcseitfnpcdg,ilaRenurd-sZhfwiLADendmhguot-acnieslgxMvtac.rensd,iIgptoHeanPws,ropef3acdtT8ghso4eu–nAi37sN98ge4–od.c3is2af0tm1hobeni.gfAuICtramLio2nk0es1pyutaSnmsioef:arl ofthe 25th international conference on Machine learning, pages 160–167. Marie-Catherine de Marneffe, Christopher D. Manning, and Christopher provocative. Potts. Learning 2010. Was it good? the meaning It was of scalar adjec- tives. In Proceedings of the 48th Meeting of the Association for Computational Linguistics, pages 167–176. Christiane Fellbaum. 1998. WordNet: An electronic lexical database. MIT Press. Eric H. Huang, Richard Socher, Christopher D. Manning, and Andrew Y Ng. 2012. Improving word representations via global context and multiple word prototypes. In Proceedings ofthe 50thAnnualMeeting oftheAssociation for Computational Linguistics, pages 873–882. Association for Computational Linguistics. Thomas K. Landauer, Peter W. Foltz, and Darrell Laham. 1998. An introduction to latent semantic analysis. Discourse Processes, 25:259–284. Tomas Mikolov, Martin Karafi´ at, Luk a´ˇ s Burget, Jan Cernocky, and Sanjeev Khudanpur. 2010. Recurrent neural network based language model. In Proceedings of Interspeech, pages 1045–1048. Tomas Mikolov, Daniel Povey, Luk a´ˇ s Burget, and Jan Cernocky. 2011. Strategies for training large scale neural network language models. In Proceedings of ASRU, pages 196–201 . Tomas Mikolov, Wen-tau Yih, and Geoffrey Zweig. 2013. Linguistic regularities in continuous space word representations. In Proceedings of NAACL-HLT, pages 746–751. Mitra Mohtarami, Hadi Amiri, Man Lan, and Chew Lim Tan. 2011. Predicting the uncertainty of sentiment adjectives in indirect answers. In Proceedings of the 20th ACM international conference on Information and knowledge management, pages 2485–2488. Mitra Mohtarami, Hadi Amiri, Man Lan, Thanh Phu Tran, and Chew Lim Tan. 2012. Sense sentiment similarity: an analysis. In Proceedings of the 26th AAAI Conference on Artificial Intelligence, pages 1706– 1712. Holger Schwenk. 2007. Continuous space language models. Computer Speech & Language, 21(3):492– 518. Joseph Turian, Lev Ratinov, and Yoshua Bengio. 2010. Word representations: a simple and general method for 1630