@inproceedings{sjoblom-etal-2018-paraphrase,
title = "Paraphrase Detection on Noisy Subtitles in Six Languages",
author = {Sj{\"o}blom, Eetu and
Creutz, Mathias and
Aulamo, Mikko},
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the 2018 {EMNLP} Workshop W-{NUT}: The 4th Workshop on Noisy User-generated Text",
month = nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6109",
doi = "10.18653/v1/W18-6109",
pages = "64--73",
abstract = "We perform automatic paraphrase detection on subtitle data from the Opusparcus corpus comprising six European languages: German, English, Finnish, French, Russian, and Swedish. We train two types of supervised sentence embedding models: a word-averaging (WA) model and a gated recurrent averaging network (GRAN) model. We find out that GRAN outperforms WA and is more robust to noisy training data. Better results are obtained with more and noisier data than less and cleaner data. Additionally, we experiment on other datasets, without reaching the same level of performance, because of domain mismatch between training and test data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sjoblom-etal-2018-paraphrase">
<titleInfo>
<title>Paraphrase Detection on Noisy Subtitles in Six Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eetu</namePart>
<namePart type="family">Sjöblom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathias</namePart>
<namePart type="family">Creutz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikko</namePart>
<namePart type="family">Aulamo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</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>We perform automatic paraphrase detection on subtitle data from the Opusparcus corpus comprising six European languages: German, English, Finnish, French, Russian, and Swedish. We train two types of supervised sentence embedding models: a word-averaging (WA) model and a gated recurrent averaging network (GRAN) model. We find out that GRAN outperforms WA and is more robust to noisy training data. Better results are obtained with more and noisier data than less and cleaner data. Additionally, we experiment on other datasets, without reaching the same level of performance, because of domain mismatch between training and test data.</abstract>
<identifier type="citekey">sjoblom-etal-2018-paraphrase</identifier>
<identifier type="doi">10.18653/v1/W18-6109</identifier>
<location>
<url>https://aclanthology.org/W18-6109</url>
</location>
<part>
<date>2018-11</date>
<extent unit="page">
<start>64</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Paraphrase Detection on Noisy Subtitles in Six Languages
%A Sjöblom, Eetu
%A Creutz, Mathias
%A Aulamo, Mikko
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F sjoblom-etal-2018-paraphrase
%X We perform automatic paraphrase detection on subtitle data from the Opusparcus corpus comprising six European languages: German, English, Finnish, French, Russian, and Swedish. We train two types of supervised sentence embedding models: a word-averaging (WA) model and a gated recurrent averaging network (GRAN) model. We find out that GRAN outperforms WA and is more robust to noisy training data. Better results are obtained with more and noisier data than less and cleaner data. Additionally, we experiment on other datasets, without reaching the same level of performance, because of domain mismatch between training and test data.
%R 10.18653/v1/W18-6109
%U https://aclanthology.org/W18-6109
%U https://doi.org/10.18653/v1/W18-6109
%P 64-73
Markdown (Informal)
[Paraphrase Detection on Noisy Subtitles in Six Languages](https://aclanthology.org/W18-6109) (Sjöblom et al., WNUT 2018)
ACL
- Eetu Sjöblom, Mathias Creutz, and Mikko Aulamo. 2018. Paraphrase Detection on Noisy Subtitles in Six Languages. In Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text, pages 64–73, Brussels, Belgium. Association for Computational Linguistics.