Abstract
Word embedding models typically learn dense and fixed-length vectors based on local word collocation patterns in a text corpus. Recent studies have discovered that these models often underestimate similarities between similar words and overestimate similarities between distant words. This leads to word similarity results obtained from word embedding models inconsistent with human judgment. A number of manifold learning-based word re-embedding methods are proposed to address this problem by re-embedding word vectors from the original embedding space to a new embedding space. However, these methods perform a weighted locally linear combination of embeddings of words and their neighbors twice. Besides, the reconstruction weights are easily influenced by the selection of word neighbors and the whole combination process is very time-consuming. In this paper, we introduce a novel word re-embedding method based on local tangent information to re-embed word vectors into a refined new space. Unlike previous approaches, our method re-embeds word vectors by aligning original and new embedding spaces based on the tangent information instead of performing weighted locally linear combination twice. To validate the proposed method, experiments were conducted on two standard evaluation tasks. The experimental results show that our method achieves better performance than state-of-the-art methods for word re-embedding.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Esposito, M., Damiano, E., Minutolo, A., De Pietro, G., Fujita, H.: Hybrid query expansion using lexical resources and word embeddings for sentence retrieval in question answering. Inf. Sci. 514, 88–105 (2020)
Bagheri, E., Ensan, F., Al-Obeidat, F.: Neural word and entity embeddings for ad hoc retrieval. Inf. Process. Manag. 54(4), 657–673 (2018)
Devlin, J., Zbib, R., Huang, Z., Lamar, T., Schwartz, R. M., Makhoul, J.: Fast and robust neural network joint models for statistical machine translation. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL), vol. 1, pp. 1370–1380 (2014)
Collobert, R.: Deep learning for efficient discriminative parsing. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 224–232 (2011)
Turian, J., Lev, R., Yoshua, B.: Word representations: a simple and general method for semi-supervised learning. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 384–394. Association for Computational Linguistics (ACL) (2010)
Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), vol. 1631, pp. 1631–1642. Citeseer (2013b)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), Minneapolis, MN, USA, pp. 4171–4186 (2018)
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12(1), 2493–2537 (2011)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: Proceedings of Workshop at International Conference on Learning Representations (ICLR), Scottsdale, Arizona, pp. 3111–3119 (2013a)
Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)
Qiu, L., Cao, Y., Nie, Z., Yu, Y., Rui, Y.: Learning word representation considering proximity and ambiguity. In: Proceedings of Twenty-Eighth AAAI Conference on Artificial Intelligence, pp. 1572–1578 (2014)
Peng, X., Zhou, D.: A framework for learning cross-lingual word embedding with topics. In: Wang, X., Zhang, R., Lee, Y.-K., Sun, L., Moon, Y.-S. (eds.) APWeb-WAIM 2020. LNCS, vol. 12318, pp. 285–293. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60290-1_22
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. In: Proceedings of the 8th International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia, pp. 1–17 (2020)
Liu, W., Zhou, P., Wang, Z., Zhao, Z., Deng, H., Ju, Q.: FastBERT: a self-distilling BERT with adaptive inference time. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 6035–6044 (2020)
Hasan, S., Curry, E.: Word re-embedding via manifold dimensionality retention. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 321–326 (2017)
Chu, Y., Lin, H., Yang, L., Diao, Y., Zhang, S., Fan, X.: Refining word representations by manifold learning. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), pp. 5394–5400 (2019)
Zhang, Z., Zha, H.: Principal manifolds and nonlinear dimension reduction via local tangent space alignment. J. Shanghai Univ. 8(4), 406–424 (2002)
Zhang, Z., Zha, H.: Nonlinear dimension reduction via local tangent space alignment. In: Liu, J., Cheung, Y., Yin, H. (eds.) IDEAL 2003. LNCS, vol. 2690, pp. 477–481. Springer, Heidelberg (2003). https://doi.org/10.1007/978-3-540-45080-1_66
Salton, G., Wong, A., Yang, C.S.: A vector space model for automatic indexing. Commun. ACM 18(11), 613–620 (1975)
Deerwester, S., Dumais, S.T., Furnas, G.W., Landauer, T.K., Harshman, R.: Indexing by latent semantic analysis. J. Am. Soc. Inf. Sci. 41(6), 391–407 (1990)
Lund, K., Burgess, C.: Producing high-dimensional semantic spaces from lexical co-occurrence. Behav. Res. Methods Instrum. Comput. 28(2), 203–208 (1996)
Dhillon, P., Foster, D.P., Ungar, L.H.: Multi-view learning of word embeddings via CCA. Advances in Neural Information Processing Systems, pp. 199–207 (2011)
Lebret, R., Collobert, R.: Word embeddings through hellinger PCA. In: Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics. Idiap, pp. 482–490 (2013)
Hinton, G.E.: Learning distributed representations of concepts. In: Proceedings of the Eighth Annual Conference of the Cognitive Science Society, vol. 1, pp. 1–12 (1986)
Bengio, Y., Ducharme, R., Vincent, P., Jauvin, C.: A neural probabilistic language model. J. Mach. Learn. Res. 3(1), 1137–1155 (2003)
Bengio, Y., Senécal, J.S.: Quick training of probabilistic neural nets by importance sampling. In: Proceedings of the Conference on Artificial Intelligence and Statistics (AISTATS), pp. 1–9 (2003)
Mnih, A., Hinton, G.: Three new graphical models for statistical language modelling. In: Proceedings of the 24th International Conference on Machine Learning, pp. 641–648 (2007)
Collobert, R., Weston, J.: A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of the 25th International Conference on Machine Learning, pp. 160–167 (2008)
Chaudhary, A., Zhou, C., Levin, L., Neubig, G., Mortensen, D.R., Carbonell, J.G.: Adapting word embeddings to new languages with morphological and phonological subword representations. arXiv preprint arXiv:1808.09500 (2018)
Kolyvakis, P., Kalousis, A., Kiritsis, D.: Deepalignment: Unsupervised ontology matching with refined word vectors. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 787–798 (2018)
Seyeditabari, A., Tabari, N., Gholizadeh, S., Zadrozny, W.: Emotional embeddings: refining word embeddings to capture emotional content of words. arXiv preprint arXiv:1906.00112 (2019)
Utsumi. A.: Refining pretrained word embeddings using layer-wise relevance propagation. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 4840–4846 (2018)
Yu, L.C., Wang, J., Lai, K.R., Zhang, X.: Refining word embeddings using intensity scores for sentiment analysis. IEEE Trans. Audio Speech Lang. Process. 26(3), 671–681 (2017)
Mu, J., Bhat, S., Viswanath, P.: All-but-the-top: simple and effective postprocessing for word representations. In: Proceedings of Poster at 6th International Conference on Learning Representations (ICLR), 1–25 (2018)
Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)
Bruni, E., Tran, N.K., Baroni, M.: Multimodal distributional semantics. J. Artif. Intell. Res. 49(1), 1–47 (2014)
Agirre, E., Alfonseca, E., Hall, K.B., Kravalova, J., Pasca, M., Soroa, A.: A study on similarity and relatedness using distributional and wordnet-based approaches. In: Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL), pp. 19–27 (2009)
Kira, R., Agichtein, E., Gabrilovich, E.: A word at a time: computing word relatedness using temporal semantic analysis. In: Proceedings of the 20th International Conference on World Wide Web (WWW), pp. 337–346 (2011)
Rubenstein, H., Goodenough, J.B.: Contextual correlates of synonymy. Commun. ACM 8(10), 627–633 (1965)
Finkelstein, L., Gabrilovich, E., Matias, Y.: Placing search in context: the concept revisited. In: Proceedings of the 10th International Conference on World Wide Web (WWW), pp. 406–414 (2001)
Hill, F., Korhonen, A.: Simlex-999: evaluating semantic models with (genuine) similarity estimation. Comput. Linguist. 41(4), 665–695 (2015)
Gerz, D., Vulić, I., Hill, F., Reichart, R., Korhonen, A.: Simverb-3500: a large-scale evaluation set of verb similarity. arXiv preprint arXiv:1608.00869 (2016)
Acknowledgements
We would like to thank anonymous reviewers for their helpful comments and suggestions. This work was supported by the National Natural Science Foundation of China under Project No. 61876062 and General Key Laboratory for Complex System Simulation under Project No. XM2020XT1004.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhao, W., Zhou, D., Li, L., Chen, J. (2021). Utilizing Local Tangent Information for Word Re-embedding. In: Hiemstra, D., Moens, MF., Mothe, J., Perego, R., Potthast, M., Sebastiani, F. (eds) Advances in Information Retrieval. ECIR 2021. Lecture Notes in Computer Science(), vol 12656. Springer, Cham. https://doi.org/10.1007/978-3-030-72113-8_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-72113-8_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-72112-1
Online ISBN: 978-3-030-72113-8
eBook Packages: Computer ScienceComputer Science (R0)