{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T08:32:26Z","timestamp":1790065946757,"version":"4.0.1"},"reference-count":30,"publisher":"Cambridge University Press (CUP)","issue":"1","license":[{"start":{"date-parts":[[2017,9,4]],"date-time":"2017-09-04T00:00:00Z","timestamp":1504483200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Nat. Lang. Eng."],"published-print":{"date-parts":[[2018,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Neural Network-based approaches have recently produced good performances in Natural language tasks, such as Supertagging. In the supertagging task, a Supertag (Lexical category) is assigned to each word in an input sequence. Combinatory Categorial Grammar Supertagging is a more challenging problem than various sequence-tagging problems, such as part-of-speech (POS) tagging and named entity recognition due to the large number of the lexical categories. Specifically, simple Recurrent Neural Network (RNN) has shown to significantly outperform the previous state-of-the-art feed-forward neural networks. On the other hand, it is well known that Recurrent Networks fail to learn long dependencies. In this paper, we introduce a new neural network architecture based on backward and Bidirectional Long Short-Term Memory (BLSTM) Networks that has the ability to memorize information for long dependencies and benefit from both past and future information. State-of-the-art methods focus on previous information, whereas BLSTM has access to information in both previous and future directions. Our main findings are that bidirectional networks outperform unidirectional ones, and Long Short-Term Memory (LSTM) networks are more precise and successful than both unidirectional and bidirectional standard RNNs. Experiment results reveal the effectiveness of our proposed method on both in-domain and out-of-domain datasets. Experiments show improvements about (1.2 per cent) over standard RNN.<\/jats:p>","DOI":"10.1017\/s1351324917000250","type":"journal-article","created":{"date-parts":[[2017,9,4]],"date-time":"2017-09-04T06:48:02Z","timestamp":1504507682000},"page":"77-90","source":"Crossref","is-referenced-by-count":7,"title":["CCG supertagging with bidirectional long short-term memory networks"],"prefix":"10.1017","volume":"24","author":[{"given":"REKIA","family":"KADARI","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"YU","family":"ZHANG","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"WEINAN","family":"ZHANG","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"TING","family":"LIU","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"56","published-online":{"date-parts":[[2017,9,4]]},"reference":[{"key":"S1351324917000250_ref027","first-page":"707","volume-title":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing","author":"Wang","year":"2015"},{"key":"S1351324917000250_ref001","first-page":"237","article-title":"Supertagging: an approach to almost parsing","volume":"25","author":"Bangalore","year":"1999","journal-title":"Computational Linguistics"},{"key":"S1351324917000250_ref006","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220396"},{"key":"S1351324917000250_ref003","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1162\/tacl_a_00104","article-title":"Named entity recognition with bidirectional lstm-cnns","volume":"4","author":"Chiu","year":"2016","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"S1351324917000250_ref010","first-page":"6645","volume-title":"Proceedings of the IEEE International Conference Acoustics, Speech and Signal Processing (ICASSP)","author":"Graves","year":"2013"},{"key":"S1351324917000250_ref023","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/6591.001.0001","volume-title":"The Syntactic Process","author":"Steedman","year":"2000"},{"key":"S1351324917000250_ref018","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163930"},{"key":"S1351324917000250_ref009","unstructured":"Gers F. 2001. Long Short-Term Memory in Recurrent Neural Networks. PhD Thesis, Ecole Polytechnique Federale de Lausanne, Lausanne, Switzerland."},{"key":"S1351324917000250_ref015","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1162\/tacl_a_00186","article-title":"Improved CCG parsing with semi-supervised supertagging","volume":"2","author":"Lewis","year":"2014","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"S1351324917000250_ref028","unstructured":"Wang P. , Qian Y. , Soong F. K. , He L. , and Zhao H. 2015. Part-of-speech tagging with bidirectional long short-term memory recurrent neural network. arXiv preprint arXiv: 1510.0618."},{"key":"S1351324917000250_ref005","unstructured":"Chollet F. 2015. Keras. https:\/\/github.com\/fchollet\/keras."},{"key":"S1351324917000250_ref029","first-page":"250","volume-title":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (ACL)","author":"Xu","year":"2015"},{"key":"S1351324917000250_ref021","first-page":"50","article-title":"Bioinfer: a corpus for information extraction in the biomedical domain","volume":"8","author":"Pyysalo","year":"2007","journal-title":"BioMed Central Bioinformatics"},{"key":"S1351324917000250_ref024","doi-asserted-by":"publisher","DOI":"10.1002\/9781444395037.ch5"},{"key":"S1351324917000250_ref014","first-page":"221","volume-title":"Proceedings of the 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): Human Language Technologies, Association for Computational Linguistics","author":"Lewis","year":"2016"},{"key":"S1351324917000250_ref011","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"S1351324917000250_ref025","first-page":"384","volume-title":"Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics","author":"Turian","year":"2010"},{"key":"S1351324917000250_ref026","first-page":"232","volume-title":"Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)","author":"Vaswani","year":"2016"},{"key":"S1351324917000250_ref020","first-page":"285","volume-title":"Proceedings of the 14th International Conferenace Frontiers in Handwriting Recognition (ICFHR)","author":"Pham","year":"2014"},{"key":"S1351324917000250_ref016","first-page":"1299","volume-title":"Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL)","author":"Ling","year":"2015"},{"key":"S1351324917000250_ref008","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"Collobert","year":"2011","journal-title":"The Journal of Machine Learning Research"},{"key":"S1351324917000250_ref017","first-page":"313","article-title":"Building a large annotated corpus of English: the Penn Treebank","volume":"19","author":"Marcus","year":"1993","journal-title":"Computational Linguistics"},{"key":"S1351324917000250_ref019","first-page":"3111","volume-title":"Advances in Neural Information Processing Systems","author":"Mikolov","year":"2013"},{"key":"S1351324917000250_ref007","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2007.33.4.493"},{"key":"S1351324917000250_ref030","unstructured":"Zeiler M. D. 2012. ADADELTA: an adaptive learning rate method. arXiv preprint arXiv: 1212.5701."},{"key":"S1351324917000250_ref012","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2007.33.3.355"},{"key":"S1351324917000250_ref013","first-page":"38","volume-title":"Proceedings of the 2009 Workshop on The People\u2019s Web Meets NLP: Collaboratively Constructed Semantic Resources, Association for Computational Linguistics","author":"Honnibal","year":"2009"},{"key":"S1351324917000250_ref002","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(95)00108-5"},{"key":"S1351324917000250_ref004","first-page":"103","volume-title":"Proceedings of 8th Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-8)","author":"Cho","year":"2014"},{"key":"S1351324917000250_ref022","first-page":"475","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-08), Association for Computational Linguistics","author":"Rimell","year":"2008"}],"container-title":["Natural Language Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1351324917000250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T14:45:36Z","timestamp":1750862736000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1351324917000250\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9,4]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,1]]}},"alternative-id":["S1351324917000250"],"URL":"https:\/\/doi.org\/10.1017\/s1351324917000250","relation":{},"ISSN":["1351-3249","1469-8110"],"issn-type":[{"value":"1351-3249","type":"print"},{"value":"1469-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,9,4]]}}}