{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T16:17:03Z","timestamp":1772122623559,"version":"3.50.1"},"reference-count":30,"publisher":"Cambridge University Press (CUP)","issue":"4","license":[{"start":{"date-parts":[[2019,7,31]],"date-time":"2019-07-31T00:00:00Z","timestamp":1564531200000},"content-version":"unspecified","delay-in-days":30,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Nat. Lang. Eng."],"published-print":{"date-parts":[[2019,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Sentence-level representations are necessary for various natural language processing tasks. Recurrent neural networks have proven to be very effective in learning distributed representations and can be trained efficiently on natural language inference tasks. We build on top of one such model and propose a hierarchy of bidirectional LSTM and max pooling layers that implements an iterative refinement strategy and yields state of the art results on the SciTail dataset as well as strong results for Stanford Natural Language Inference and Multi-Genre Natural Language Inference. We can show that the sentence embeddings learned in this way can be utilized in a wide variety of transfer learning tasks, outperforming InferSent on 7 out of 10 and SkipThought on 8 out of 9 SentEval sentence embedding evaluation tasks. Furthermore, our model beats the InferSent model in 8 out of 10 recently published SentEval probing tasks designed to evaluate sentence embeddings\u2019 ability to capture some of the important linguistic properties of sentences.<\/jats:p>","DOI":"10.1017\/s1351324919000202","type":"journal-article","created":{"date-parts":[[2019,7,31]],"date-time":"2019-07-31T11:33:09Z","timestamp":1564572789000},"page":"467-482","source":"Crossref","is-referenced-by-count":23,"title":["Sentence embeddings in NLI with iterative refinement encoders"],"prefix":"10.1017","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3573-5993","authenticated-orcid":false,"given":"Aarne","family":"Talman","sequence":"first","affiliation":[]},{"given":"Anssi","family":"Yli-Jyr\u00e4","sequence":"additional","affiliation":[]},{"given":"J\u00f6rg","family":"Tiedemann","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2019,7,31]]},"reference":[{"key":"S1351324919000202_ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5310"},{"key":"S1351324919000202_ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1244"},{"key":"S1351324919000202_ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"S1351324919000202_ref12","first-page":"107","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)","author":"Gururangan","year":"2018"},{"key":"S1351324919000202_ref17","unstructured":"Maas A.L. , Hannun A.Y. and Ng A.Y. (2013). Rectifier nonlinearities improve neural network acoustic models. In International Conference on Machine Learning."},{"key":"S1351324919000202_ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1070"},{"key":"S1351324919000202_ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1185"},{"key":"S1351324919000202_ref14","doi-asserted-by":"crossref","unstructured":"Khot T. , Sabharwal A. and Clark P. (2018). Scitail: A textual entailment dataset from science question answering. In AAAI Conference on Artificial Intelligence.","DOI":"10.1609\/aaai.v32i1.12022"},{"key":"S1351324919000202_ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1152"},{"key":"S1351324919000202_ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S18-2023"},{"key":"S1351324919000202_ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5311"},{"key":"S1351324919000202_ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2103"},{"key":"S1351324919000202_ref15","unstructured":"Kingma D.P. and Ba J. (2015). Adam: A method for stochastic optimization. In International Conference on Learning Representations (ICLR)."},{"key":"S1351324919000202_ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1139"},{"key":"S1351324919000202_ref4","unstructured":"Chatzikyriakidis S. , Cooper R. , Dobnik S. and Larsson S. (2017). An overview of natural language inference data collection: The way forward? In Proceedings of the Computing Natural Language Inference Workshop."},{"key":"S1351324919000202_ref5","first-page":"1815","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics","author":"Chen","year":"2018"},{"key":"S1351324919000202_ref8","first-page":"1699","volume-title":"Proceedings of the 11th Language Resources and Evaluation Conference. European Language Resource Association","author":"Conneau","year":"2018"},{"key":"S1351324919000202_ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1198"},{"key":"S1351324919000202_ref13","first-page":"11367","volume-title":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Hill","year":"2016"},{"key":"S1351324919000202_ref16","first-page":"3294","volume-title":"Advances in Neural Information Processing Systems 28","author":"Kiros","year":"2015"},{"key":"S1351324919000202_ref18","first-page":"3111","volume-title":"Advances in Neural Information Processing Systems 26","author":"Mikolov","year":"2013"},{"key":"S1351324919000202_ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2022"},{"key":"S1351324919000202_ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5308"},{"key":"S1351324919000202_ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"S1351324919000202_ref24","unstructured":"Talman A. and Chatzikyriakidis S. (2019). Testing the generalization power of neural network models across NLI benchmarks. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. arXiv:1810.09774."},{"key":"S1351324919000202_ref28","first-page":"1112","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)","author":"Williams","year":"2018"},{"key":"S1351324919000202_ref29","unstructured":"Yoon D. , Lee D. and Lee S. (2018). Dynamic Self-Attention : Computing Attention over Words Dynamically for Sentence Embedding. arXiv:1808.07383."},{"key":"S1351324919000202_ref30","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"S1351324919000202_ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5307"},{"key":"S1351324919000202_ref26","unstructured":"Vendrov I. , Kiros R. , Fidler S. and Urtasun R. (2016). Order-embeddings of images and language. In 6th International Conference on Learning Representations."}],"container-title":["Natural Language Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1351324919000202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,24]],"date-time":"2022-09-24T22:59:28Z","timestamp":1664060368000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1351324919000202\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":30,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,7]]}},"alternative-id":["S1351324919000202"],"URL":"https:\/\/doi.org\/10.1017\/s1351324919000202","relation":{},"ISSN":["1351-3249","1469-8110"],"issn-type":[{"value":"1351-3249","type":"print"},{"value":"1469-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7]]}}}