Sentence Embeddings in NLI with Iterative Refinement Encoders

Näytä kaikki kuvailutiedot



Pysyväisosoite

http://hdl.handle.net/10138/304483

Lähdeviite

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

Julkaisun nimi: Sentence Embeddings in NLI with Iterative Refinement Encoders
Tekijä: Talman, Aarne Johannes; Yli-Jyrä, Anssi; Tiedemann, Jörg
Muu tekijä: University of Helsinki, Department of Digital Humanities
University of Helsinki, Language Technology
University of Helsinki, Department of Digital Humanities
Päiväys: 2019-07-31
Kieli: eng
Sivumäärä: 16
Kuuluu julkaisusarjaan: Natural Language Engineering
URI: http://hdl.handle.net/10138/304483
Tiivistelmä: 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.
Avainsanat: 113 Computer and information sciences
6121 Languages
Tekijänoikeustiedot:


Tiedostot

Latausmäärä yhteensä: Ladataan...

Tiedosto(t) Koko Formaatti Näytä
1808.08762_1.pdf 477.1KB PDF Avaa tiedosto

Viite kuuluu kokoelmiin:

Näytä kaikki kuvailutiedot