Sentence Embeddings in NLI with Iterative Refinement Encoders

Show simple item record

dc.contributor University of Helsinki, Department of Digital Humanities en
dc.contributor University of Helsinki, Language Technology en
dc.contributor University of Helsinki, Department of Digital Humanities en
dc.contributor.author Talman, Aarne Johannes
dc.contributor.author Yli-Jyrä, Anssi
dc.contributor.author Tiedemann, Jörg
dc.date.accessioned 2019-08-12T06:58:01Z
dc.date.available 2019-08-12T06:58:01Z
dc.date.issued 2019-07-31
dc.identifier.citation Talman , A J , Yli-Jyrä , A & Tiedemann , J 2019 , ' Sentence Embeddings in NLI with Iterative Refinement Encoders ' , Natural Language Engineering , vol. 25 , no. 4 , pp. 467-482 . https://doi.org/10.1017/s1351324919000202 en
dc.identifier.other PURE: 125082713
dc.identifier.other PURE UUID: f56f5d09-183f-4a7d-868d-1fcd4a53e4c0
dc.identifier.other Scopus: 85070091023
dc.identifier.other ORCID: /0000-0003-0731-2114/work/60609270
dc.identifier.other ORCID: /0000-0003-3065-7989/work/60613526
dc.identifier.other ORCID: /0000-0002-3573-5993/work/60613546
dc.identifier.other WOS: 000477972600004
dc.identifier.uri http://hdl.handle.net/10138/304483
dc.description.abstract Sentence-level representations are necessary for various NLP 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 BiLSTM 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 SNLI and MultiNLI. 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' ability to capture some of the important linguistic properties of sentences. en
dc.format.extent 16
dc.language.iso eng
dc.relation.ispartof Natural Language Engineering
dc.relation.uri https://arxiv.org/pdf/1808.08762.pdf
dc.rights en
dc.subject 113 Computer and information sciences en
dc.subject 6121 Languages en
dc.title Sentence Embeddings in NLI with Iterative Refinement Encoders en
dc.type Article
dc.description.version Peer reviewed
dc.identifier.doi https://doi.org/10.1017/s1351324919000202
dc.type.uri info:eu-repo/semantics/other
dc.type.uri info:eu-repo/semantics/acceptedVersion
dc.contributor.pbl
dc.contributor.pbl

Files in this item

Total number of downloads: Loading...

Files Size Format View
1808.08762_1.pdf 477.1Kb PDF View/Open

This item appears in the following Collection(s)

Show simple item record