@article{xu-etal-2014-extracting,
title = "Extracting Lexically Divergent Paraphrases from {T}witter",
author = "Xu, Wei and
Ritter, Alan and
Callison-Burch, Chris and
Dolan, William B. and
Ji, Yangfeng",
editor = "Lin, Dekang and
Collins, Michael and
Lee, Lillian",
journal = "Transactions of the Association for Computational Linguistics",
volume = "2",
year = "2014",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/Q14-1034",
doi = "10.1162/tacl_a_00194",
pages = "435--448",
abstract = "We present MultiP (Multi-instance Learning Paraphrase Model), a new model suited to identify paraphrases within the short messages on Twitter. We jointly model paraphrase relations between word and sentence pairs and assume only sentence-level annotations during learning. Using this principled latent variable model alone, we achieve the performance competitive with a state-of-the-art method which combines a latent space model with a feature-based supervised classifier. Our model also captures lexically divergent paraphrases that differ from yet complement previous methods; combining our model with previous work significantly outperforms the state-of-the-art. In addition, we present a novel annotation methodology that has allowed us to crowdsource a paraphrase corpus from Twitter. We make this new dataset available to the research community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2014-extracting">
<titleInfo>
<title>Extracting Lexically Divergent Paraphrases from Twitter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Callison-Burch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Dolan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangfeng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>We present MultiP (Multi-instance Learning Paraphrase Model), a new model suited to identify paraphrases within the short messages on Twitter. We jointly model paraphrase relations between word and sentence pairs and assume only sentence-level annotations during learning. Using this principled latent variable model alone, we achieve the performance competitive with a state-of-the-art method which combines a latent space model with a feature-based supervised classifier. Our model also captures lexically divergent paraphrases that differ from yet complement previous methods; combining our model with previous work significantly outperforms the state-of-the-art. In addition, we present a novel annotation methodology that has allowed us to crowdsource a paraphrase corpus from Twitter. We make this new dataset available to the research community.</abstract>
<identifier type="citekey">xu-etal-2014-extracting</identifier>
<identifier type="doi">10.1162/tacl_a_00194</identifier>
<location>
<url>https://aclanthology.org/Q14-1034</url>
</location>
<part>
<date>2014</date>
<detail type="volume"><number>2</number></detail>
<extent unit="page">
<start>435</start>
<end>448</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Extracting Lexically Divergent Paraphrases from Twitter
%A Xu, Wei
%A Ritter, Alan
%A Callison-Burch, Chris
%A Dolan, William B.
%A Ji, Yangfeng
%J Transactions of the Association for Computational Linguistics
%D 2014
%V 2
%I MIT Press
%C Cambridge, MA
%F xu-etal-2014-extracting
%X We present MultiP (Multi-instance Learning Paraphrase Model), a new model suited to identify paraphrases within the short messages on Twitter. We jointly model paraphrase relations between word and sentence pairs and assume only sentence-level annotations during learning. Using this principled latent variable model alone, we achieve the performance competitive with a state-of-the-art method which combines a latent space model with a feature-based supervised classifier. Our model also captures lexically divergent paraphrases that differ from yet complement previous methods; combining our model with previous work significantly outperforms the state-of-the-art. In addition, we present a novel annotation methodology that has allowed us to crowdsource a paraphrase corpus from Twitter. We make this new dataset available to the research community.
%R 10.1162/tacl_a_00194
%U https://aclanthology.org/Q14-1034
%U https://doi.org/10.1162/tacl_a_00194
%P 435-448
Markdown (Informal)
[Extracting Lexically Divergent Paraphrases from Twitter](https://aclanthology.org/Q14-1034) (Xu et al., TACL 2014)
ACL