@inproceedings{wu-etal-2018-phrase,
title = "Phrase-level Self-Attention Networks for Universal Sentence Encoding",
author = "Wu, Wei and
Wang, Houfeng and
Liu, Tianyu and
Ma, Shuming",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1408",
doi = "10.18653/v1/D18-1408",
pages = "3729--3738",
abstract = "Universal sentence encoding is a hot topic in recent NLP research. Attention mechanism has been an integral part in many sentence encoding models, allowing the models to capture context dependencies regardless of the distance between the elements in the sequence. Fully attention-based models have recently attracted enormous interest due to their highly parallelizable computation and significantly less training time. However, the memory consumption of their models grows quadratically with the sentence length, and the syntactic information is neglected. To this end, we propose Phrase-level Self-Attention Networks (PSAN) that perform self-attention across words inside a phrase to capture context dependencies at the phrase level, and use the gated memory updating mechanism to refine each word{'}s representation hierarchically with longer-term context dependencies captured in a larger phrase. As a result, the memory consumption can be reduced because the self-attention is performed at the phrase level instead of the sentence level. At the same time, syntactic information can be easily integrated in the model. Experiment results show that PSAN can achieve the state-of-the-art performance across a plethora of NLP tasks including binary and multi-class classification, natural language inference and sentence similarity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2018-phrase">
<titleInfo>
<title>Phrase-level Self-Attention Networks for Universal Sentence Encoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houfeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuming</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Universal sentence encoding is a hot topic in recent NLP research. Attention mechanism has been an integral part in many sentence encoding models, allowing the models to capture context dependencies regardless of the distance between the elements in the sequence. Fully attention-based models have recently attracted enormous interest due to their highly parallelizable computation and significantly less training time. However, the memory consumption of their models grows quadratically with the sentence length, and the syntactic information is neglected. To this end, we propose Phrase-level Self-Attention Networks (PSAN) that perform self-attention across words inside a phrase to capture context dependencies at the phrase level, and use the gated memory updating mechanism to refine each word’s representation hierarchically with longer-term context dependencies captured in a larger phrase. As a result, the memory consumption can be reduced because the self-attention is performed at the phrase level instead of the sentence level. At the same time, syntactic information can be easily integrated in the model. Experiment results show that PSAN can achieve the state-of-the-art performance across a plethora of NLP tasks including binary and multi-class classification, natural language inference and sentence similarity.</abstract>
<identifier type="citekey">wu-etal-2018-phrase</identifier>
<identifier type="doi">10.18653/v1/D18-1408</identifier>
<location>
<url>https://aclanthology.org/D18-1408</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>3729</start>
<end>3738</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Phrase-level Self-Attention Networks for Universal Sentence Encoding
%A Wu, Wei
%A Wang, Houfeng
%A Liu, Tianyu
%A Ma, Shuming
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F wu-etal-2018-phrase
%X Universal sentence encoding is a hot topic in recent NLP research. Attention mechanism has been an integral part in many sentence encoding models, allowing the models to capture context dependencies regardless of the distance between the elements in the sequence. Fully attention-based models have recently attracted enormous interest due to their highly parallelizable computation and significantly less training time. However, the memory consumption of their models grows quadratically with the sentence length, and the syntactic information is neglected. To this end, we propose Phrase-level Self-Attention Networks (PSAN) that perform self-attention across words inside a phrase to capture context dependencies at the phrase level, and use the gated memory updating mechanism to refine each word’s representation hierarchically with longer-term context dependencies captured in a larger phrase. As a result, the memory consumption can be reduced because the self-attention is performed at the phrase level instead of the sentence level. At the same time, syntactic information can be easily integrated in the model. Experiment results show that PSAN can achieve the state-of-the-art performance across a plethora of NLP tasks including binary and multi-class classification, natural language inference and sentence similarity.
%R 10.18653/v1/D18-1408
%U https://aclanthology.org/D18-1408
%U https://doi.org/10.18653/v1/D18-1408
%P 3729-3738
Markdown (Informal)
[Phrase-level Self-Attention Networks for Universal Sentence Encoding](https://aclanthology.org/D18-1408) (Wu et al., EMNLP 2018)
ACL