Sentence Embeddings in NLI with Iterative Refinement Encoders

Show full item record



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 .

Title: Sentence Embeddings in NLI with Iterative Refinement Encoders
Author: Talman, Aarne Johannes; Yli-Jyrä, Anssi; Tiedemann, Jörg
Contributor organization: Department of Digital Humanities
Language Technology
Date: 2019-07-31
Language: eng
Number of pages: 16
Belongs to series: Natural Language Engineering
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.
Subject: 113 Computer and information sciences
6121 Languages
Peer reviewed: Yes
Rights: unspecified
Usage restriction: openAccess
Self-archived version: acceptedVersion

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 full item record