{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T15:53:15Z","timestamp":1721145195877},"reference-count":82,"publisher":"Cambridge University Press (CUP)","issue":"3","license":[{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["Nat. Lang. Eng."],"published-print":{"date-parts":[[2023,5]]},"abstract":"Abstract<\/jats:title>Significant advances have been achieved in bilingual word-level alignment, yet the challenge remains for phrase-level alignment. Moreover, the need for parallel data is a critical drawback for the alignment task. This work proposes a system that alleviates these two problems: a unified phrase representation model using cross-lingual word embeddings as input and an unsupervised training algorithm inspired by recent works on neural machine translation. The system consists of a sequence-to-sequence architecture where a short sequence encoder constructs cross-lingual representations of phrases of any length, then an LSTM network decodes them w.r.t their contexts. After training with comparable corpora and existing key phrase extraction, our encoder provides cross-lingual phrase representations that can be compared without further transformation. Experiments on five data sets show that our method obtains state-of-the-art results on the bilingual phrase alignment task and improves the results of different length phrase alignment by a mean of 8.8<\/jats:bold> points in MAP.<\/jats:p>","DOI":"10.1017\/s1351324922000328","type":"journal-article","created":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T13:20:45Z","timestamp":1659360045000},"page":"643-668","update-policy":"http:\/\/dx.doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":1,"title":["From unified phrase representation to bilingual phrase alignment in an unsupervised manner"],"prefix":"10.1017","volume":"29","author":[{"given":"Jingshu","family":"Liu","sequence":"first","affiliation":[]},{"given":"Emmanuel","family":"Morin","sequence":"additional","affiliation":[]},{"given":"Sebastian","family":"Pe\u00f1a Saldarriaga","sequence":"additional","affiliation":[]},{"given":"Joseph","family":"Lark","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2022,8,1]]},"reference":[{"key":"S1351324922000328_ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1996.548916"},{"key":"S1351324922000328_ref11","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"S1351324922000328_ref54","doi-asserted-by":"crossref","unstructured":"Peng, X. , Lin, C. and Stevenson, M. (2021). Cross-lingual word embedding refinement by $\\ell_{1}$ norm optimisation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Online. Association for Computational Linguistics, pp. 2690\u20132701.","DOI":"10.18653\/v1\/2021.naacl-main.214"},{"key":"S1351324922000328_ref1","unstructured":"Agerri, R. , Bermudez, J. and Rigau, G. (2014). Ixa pipeline: Efficient and ready to use multilingual nlp tools. In Chair N.C.C., Choukri K., Declerck, T., Loftsson, H., Maegaard, B., Mariani, J., Moreno, A., Odijk, J. and Piperidis, S. (eds), Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914), Reykjavik, Iceland. European Language Resources Association (ELRA)."},{"key":"S1351324922000328_ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10321"},{"key":"S1351324922000328_ref30","unstructured":"He, D. , Xia, Y. , Qin, T. , Wang, L. , Yu, N. , Liu, T.-Y. and Ma, W.-Y. (2016). Dual learning for machine translation. In Advances in Neural Information Processing Systems 29 (NIPS\u201916), pp. 820\u2013828."},{"key":"S1351324922000328_ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"S1351324922000328_ref25","unstructured":"Grefenstette, G. (1999). The world wide web as a resource for example-based machine translation tasks. In Proceedings of the ASLIB Conference on Translating and the Computer 21, London, UK."},{"key":"S1351324922000328_ref71","unstructured":"Vaswani, A. , Shazeer, N. , Parmar, N. , Uszkoreit, J. , Jones, L. , Gomez, A.N. , Kaiser, L.u. and Polosukhin, I . (2017). Attention is all you need. In Advances in Neural Information Processing Systems 30 (NIPS\u201917), pp. 5998\u20136008."},{"key":"S1351324922000328_ref72","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"S1351324922000328_ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1156"},{"key":"S1351324922000328_ref15","unstructured":"Devlin, J. , Chang, M.-W. , Lee, K. and Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. CoRR, abs\/1810.04805."},{"key":"S1351324922000328_ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/E14-1049"},{"key":"S1351324922000328_ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1160"},{"key":"S1351324922000328_ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.100"},{"key":"S1351324922000328_ref24","unstructured":"Grave, E. , Bojanowski, P. , Gupta, P. , Joulin, A. and Mikolov, T. (2018). Learning word vectors for 157 languages. In Proceedings of 11th Edition of the Language Resources and Evaluation Conference (LREC\u201918), Miyazaki, Japan, pp. 3483\u20133487."},{"key":"S1351324922000328_ref29","unstructured":"Hazem, A. and Morin, E. (2017). Bilingual word embeddings for bilingual terminology extraction from specialized comparable corpora. In Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP\u201917), Taipei, Taiwan, pp. 685\u2013693."},{"key":"S1351324922000328_ref45","unstructured":"Liu, J. , Morin, E. , Pe\u00f1a Saldarriaga, S. and Lark, J. (2020). A unified and unsupervised framework for bilingual phrase alignment on specialized comparable corpora. In 24th European Conference on Artificial Intelligence (ECAI), Santiago de Compostela, Spain."},{"key":"S1351324922000328_ref52","doi-asserted-by":"publisher","DOI":"10.3115\/991886.991938"},{"key":"S1351324922000328_ref70","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2934"},{"key":"S1351324922000328_ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.527"},{"key":"S1351324922000328_ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W15-1513"},{"key":"S1351324922000328_ref28","unstructured":"Hazem, A. and Morin, E. (2016). Efficient data selection for bilingual terminology extraction from comparable corpora. In Proceedings of the 26th International Conference on Computational Linguistics (COLING\u201916), Osaka, Japan, pp. 3401\u20133411."},{"key":"S1351324922000328_ref57","unstructured":"Radford, A. , Wu, J. , Child, R. , Luan, D. , Amodei, D. and Sutskever, I. (2019). Language models are unsupervised multitask learners. https:\/\/github.com\/openai\/gpt-2."},{"key":"S1351324922000328_ref32","unstructured":"Irsoy, O. and Cardie, C. (2014). Deep recursive neural networks for compositionality in language. In Advances in Neural Information Processing Systems 27 (NIPS\u201914), pp. 2096\u20132104."},{"key":"S1351324922000328_ref55","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"S1351324922000328_ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1009"},{"key":"S1351324922000328_ref36","unstructured":"Lample, G. and Conneau, A. (2019). Cross-lingual language model pretraining. CoRR, abs\/1901.07291."},{"key":"S1351324922000328_ref60","unstructured":"Robitaille, X. , Sasaki, Y. , Tonoike, M. , Sato, S. and Utsuro, T. (2006). Compiling french-japanese terminologies from the web. In Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL\u201906), Trento, Italy, pp. 225\u2013232."},{"key":"S1351324922000328_ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"S1351324922000328_ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"S1351324922000328_ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"S1351324922000328_ref19","unstructured":"Fung, P. (1995). Compiling bilingual lexicon entries from a non-parallel english-chinese corpus. In Proceedings of the 3rd Annual Workshop on Very Large Corpora (VLC\u201995), Cambridge, MA, USA, pp. 173\u2013183."},{"key":"S1351324922000328_ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S15-1002"},{"key":"S1351324922000328_ref47","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071"},{"key":"S1351324922000328_ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1005"},{"key":"S1351324922000328_ref6","unstructured":"Bahdanau, D. , Cho, K. and Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. CoRR, abs\/1409.0473."},{"key":"S1351324922000328_ref65","unstructured":"Socher, R. , Bauer, J. , Manning, C.D. and Andrew, Y. N. (2013a). Parsing with compositional vector grammars. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL\u201913), Sofia, Bulgaria, pp. 455\u2013465."},{"key":"S1351324922000328_ref77","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1104"},{"key":"S1351324922000328_ref33","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00065"},{"key":"S1351324922000328_ref53","unstructured":"Paulus, R. , Socher, R. and Manning, C.D. (2014). Global belief recursive neural networks. In Advances in Neural Information Processing Systems 27 (NIPS\u201914), pp. 2888\u20132896."},{"key":"S1351324922000328_ref69","doi-asserted-by":"publisher","DOI":"10.3115\/1072228.1072293"},{"key":"S1351324922000328_ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1176"},{"key":"S1351324922000328_ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"S1351324922000328_ref21","unstructured":"Gehring, J. , Auli, M. , Grangier, D. , Yarats, D. and Dauphin, Y.N. (2017). Convolutional sequence to sequence learning. In Proceedings of the 34th International Conference on Machine Learning (ICML\u201917), Sydney, Australia, pp. 1243\u20131252."},{"key":"S1351324922000328_ref68","unstructured":"Sutskever, I. , Vinyals, O. and Le, Q.V. (2014). Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems 27 (NIPS\u201914), pp. 3104\u20133112."},{"key":"S1351324922000328_ref48","unstructured":"Mikolov, T. , Le, Q.V. and Sutskever, I. (2013a). Exploiting similarities among languages for machine translation. CoRR, abs\/1309.4168."},{"key":"S1351324922000328_ref26","doi-asserted-by":"publisher","DOI":"10.1080\/00437956.1954.11659520"},{"key":"S1351324922000328_ref3","doi-asserted-by":"crossref","unstructured":"Artetxe, M. , Labaka, G. and Agirre, E. (2018a). Generalizing and improving bilingual word embedding mappings with a multi-step framework of linear transformations. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI\u201918), New Orleans, LA, USA, pp. 5012\u20135019.","DOI":"10.1609\/aaai.v32i1.11992"},{"key":"S1351324922000328_ref37","unstructured":"Lample, G. , Conneau, A. , Denoyer, L. and Ranzato, M. (2018). Unsupervised machine translation using monolingual corpora only. In Proceedings of the 6th International Conference on Learning Representations (ICLR\u201918), Vancouver, Canada."},{"key":"S1351324922000328_ref61","unstructured":"Saha, A. , Khapra, M.M. , Chandar, S. , Rajendran, J. and Cho, K. (2016). A correlational encoder decoder architecture for pivot based sequence generation. In Proceedings of the 26th International Conference on Computational Linguistics (COLING\u201916), Osaka, Japan, pp. 109\u2013118."},{"key":"S1351324922000328_ref49","unstructured":"Mikolov, T. , Sutskever, I. , Chen, K. , Corrado, G.S. and Dean, J. (2013b). Distributed representations of words and phrases and their compositionality. In Advances Neural Information Processing Systems 26 (NIPS\u201913), pp. 3111\u20133119."},{"key":"S1351324922000328_ref51","unstructured":"Morin, E. and Daille, B. (2012). Revising the compositional method for terminology acquisition from comparable corpora. In Proceedings of the 24rd International Conference on Computational Linguistics (COLING\u201912), Mumbai, India, pp. 1797\u20131810."},{"key":"S1351324922000328_ref34","unstructured":"Korkontzelos, I. , Zesch, T. , Zanzotto, F.M. and Biemann, C. (2013). Semeval-2013 task 5: Evaluating phrasal semantics. In Second Joint Conference on Lexical and Computational Semantics (SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013), Atlanta, Georgia, USA. Association for Computational Linguistics, pp. 39\u201347."},{"key":"S1351324922000328_ref44","unstructured":"Liu, J. , Morin, E. and Pe\u00f1a Saldarriaga, S. (2018). Towards a unified framework for bilingual terminology extraction of single-word and multi-word terms. In Proceedings of the 27th International Conference on Computational Linguistics (COLING\u201918), Santa Fe, NM, USA, pp. 2855\u20132866."},{"key":"S1351324922000328_ref66","unstructured":"Socher, R. , Manning, C.D. and Ng, A.Y. (2010). Learning continuous phrase representations and syntactic parsing with recursive neural networks. In Proceedings of the NIPS-2010 Deep Learning and Unsupervised Feature Learning Workshop, Vancouver, Canada, pp. 1\u20139."},{"key":"S1351324922000328_ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1399"},{"key":"S1351324922000328_ref40","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1081"},{"key":"S1351324922000328_ref12","first-page":"22","article-title":"Word association norms, mutual information, and lexicography","volume":"16","author":"Church","year":"1990","journal-title":"Computational Linguistics"},{"key":"S1351324922000328_ref13","doi-asserted-by":"publisher","DOI":"10.3115\/981732.981770"},{"key":"S1351324922000328_ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6407"},{"key":"S1351324922000328_ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2002"},{"key":"S1351324922000328_ref67","unstructured":"Socher, R. , Perelygin, A. , Wu, J. , Chuang, J. , Manning, C.D. , Ng, A. and Potts, C. (2013b). Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP\u201913), Seattle, WA, USA, pp. 1631\u20131642."},{"key":"S1351324922000328_ref50","doi-asserted-by":"publisher","DOI":"10.3115\/1699510.1699567"},{"key":"S1351324922000328_ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23528-8_9"},{"key":"S1351324922000328_ref27","unstructured":"Hazem, A. and Daille, B. (2018). Word embedding approach for synonym extraction of multi-word terms. In Proceedings of the 11th edition of the Language Resources and Evaluation Conference (LREC\u201918), Miyazaki, Japan, pp. 297\u2013303."},{"key":"S1351324922000328_ref64","unstructured":"Smith, S.L. , Turban, D.H.P. , Hamblin, S. and Hammerla, N.Y. (2017). Offline bilingual word vectors, orthogonal transformations and the inverted softmax. In Proceedings of the 5th International Conference on Learning Representations (ICLR\u201917), Toulon, France."},{"key":"S1351324922000328_ref43","unstructured":"Lin, Z. , Feng, M. , dos Santos, C.N. , Yu, M. , Xiang, B. , Zhou, B . and Bengio, Y . (2017). A structured self-attentive sentence embedding. CoRR, abs\/1703.03130."},{"key":"S1351324922000328_ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"S1351324922000328_ref39","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1027"},{"key":"S1351324922000328_ref42","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00067"},{"key":"S1351324922000328_ref16","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1402_1"},{"key":"S1351324922000328_ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1026"},{"key":"S1351324922000328_ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1120"},{"key":"S1351324922000328_ref8","doi-asserted-by":"publisher","DOI":"10.3758\/BF03193020"},{"key":"S1351324922000328_ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1399"},{"key":"S1351324922000328_ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"S1351324922000328_ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299064"},{"key":"S1351324922000328_ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1250"},{"key":"S1351324922000328_ref7","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"S1351324922000328_ref59","doi-asserted-by":"publisher","DOI":"10.3115\/1034678.1034756"},{"key":"S1351324922000328_ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"}],"container-title":["Natural Language Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1351324922000328","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T07:31:39Z","timestamp":1684481499000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1351324922000328\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,1]]},"references-count":82,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["S1351324922000328"],"URL":"https:\/\/doi.org\/10.1017\/s1351324922000328","relation":{},"ISSN":["1351-3249","1469-8110"],"issn-type":[{"value":"1351-3249","type":"print"},{"value":"1469-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,1]]},"assertion":[{"value":"\u00a9 The Author(s), 2022. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}}]}}