@inproceedings{tang-etal-2017-rethinking,
title = "Rethinking Skip-thought: A Neighborhood based Approach",
author = "Tang, Shuai and
Jin, Hailin and
Fang, Chen and
Wang, Zhaowen and
de Sa, Virginia",
booktitle = "Proceedings of the 2nd Workshop on Representation Learning for {NLP}",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-2625",
doi = "10.18653/v1/W17-2625",
pages = "211--218",
abstract = "We study the skip-thought model with neighborhood information as weak supervision. More specifically, we propose a skip-thought neighbor model to consider the adjacent sentences as a neighborhood. We train our skip-thought neighbor model on a large corpus with continuous sentences, and then evaluate the trained model on 7 tasks, which include semantic relatedness, paraphrase detection, and classification benchmarks. Both quantitative comparison and qualitative investigation are conducted. We empirically show that, our skip-thought neighbor model performs as well as the skip-thought model on evaluation tasks. In addition, we found that, incorporating an autoencoder path in our model didn{'}t aid our model to perform better, while it hurts the performance of the skip-thought model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2017-rethinking">
<titleInfo>
<title>Rethinking Skip-thought: A Neighborhood based Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hailin</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaowen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Virginia</namePart>
<namePart type="family">de Sa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Representation Learning for NLP</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study the skip-thought model with neighborhood information as weak supervision. More specifically, we propose a skip-thought neighbor model to consider the adjacent sentences as a neighborhood. We train our skip-thought neighbor model on a large corpus with continuous sentences, and then evaluate the trained model on 7 tasks, which include semantic relatedness, paraphrase detection, and classification benchmarks. Both quantitative comparison and qualitative investigation are conducted. We empirically show that, our skip-thought neighbor model performs as well as the skip-thought model on evaluation tasks. In addition, we found that, incorporating an autoencoder path in our model didn’t aid our model to perform better, while it hurts the performance of the skip-thought model.</abstract>
<identifier type="citekey">tang-etal-2017-rethinking</identifier>
<identifier type="doi">10.18653/v1/W17-2625</identifier>
<location>
<url>https://aclanthology.org/W17-2625</url>
</location>
<part>
<date>2017-aug</date>
<extent unit="page">
<start>211</start>
<end>218</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rethinking Skip-thought: A Neighborhood based Approach
%A Tang, Shuai
%A Jin, Hailin
%A Fang, Chen
%A Wang, Zhaowen
%A de Sa, Virginia
%S Proceedings of the 2nd Workshop on Representation Learning for NLP
%D 2017
%8 aug
%I Association for Computational Linguistics
%C Vancouver, Canada
%F tang-etal-2017-rethinking
%X We study the skip-thought model with neighborhood information as weak supervision. More specifically, we propose a skip-thought neighbor model to consider the adjacent sentences as a neighborhood. We train our skip-thought neighbor model on a large corpus with continuous sentences, and then evaluate the trained model on 7 tasks, which include semantic relatedness, paraphrase detection, and classification benchmarks. Both quantitative comparison and qualitative investigation are conducted. We empirically show that, our skip-thought neighbor model performs as well as the skip-thought model on evaluation tasks. In addition, we found that, incorporating an autoencoder path in our model didn’t aid our model to perform better, while it hurts the performance of the skip-thought model.
%R 10.18653/v1/W17-2625
%U https://aclanthology.org/W17-2625
%U https://doi.org/10.18653/v1/W17-2625
%P 211-218
Markdown (Informal)
[Rethinking Skip-thought: A Neighborhood based Approach](https://aclanthology.org/W17-2625) (Tang et al., 2017)
ACL
- Shuai Tang, Hailin Jin, Chen Fang, Zhaowen Wang, and Virginia de Sa. 2017. Rethinking Skip-thought: A Neighborhood based Approach. In Proceedings of the 2nd Workshop on Representation Learning for NLP, pages 211–218, Vancouver, Canada. Association for Computational Linguistics.