@inproceedings{sileo-etal-2019-mining,
title = "Mining Discourse Markers for Unsupervised Sentence Representation Learning",
author = "Sileo, Damien and
Van De Cruys, Tim and
Pradel, Camille and
Muller, Philippe",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1351",
doi = "10.18653/v1/N19-1351",
pages = "3477--3486",
abstract = "Current state of the art systems in NLP heavily rely on manually annotated datasets, which are expensive to construct. Very little work adequately exploits unannotated data {--} such as discourse markers between sentences {--} mainly because of data sparseness and ineffective extraction methods. In the present work, we propose a method to automatically discover sentence pairs with relevant discourse markers, and apply it to massive amounts of data. Our resulting dataset contains 174 discourse markers with at least 10k examples each, even for rare markers such as {``}coincidentally{''} or {``}amazingly{''}. We use the resulting data as supervision for learning transferable sentence embeddings. In addition, we show that even though sentence representation learning through prediction of discourse marker yields state of the art results across different transfer tasks, it{'}s not clear that our models made use of the semantic relation between sentences, thus leaving room for further improvements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sileo-etal-2019-mining">
<titleInfo>
<title>Mining Discourse Markers for Unsupervised Sentence Representation Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Damien</namePart>
<namePart type="family">Sileo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Van De Cruys</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Camille</namePart>
<namePart type="family">Pradel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Muller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current state of the art systems in NLP heavily rely on manually annotated datasets, which are expensive to construct. Very little work adequately exploits unannotated data – such as discourse markers between sentences – mainly because of data sparseness and ineffective extraction methods. In the present work, we propose a method to automatically discover sentence pairs with relevant discourse markers, and apply it to massive amounts of data. Our resulting dataset contains 174 discourse markers with at least 10k examples each, even for rare markers such as “coincidentally” or “amazingly”. We use the resulting data as supervision for learning transferable sentence embeddings. In addition, we show that even though sentence representation learning through prediction of discourse marker yields state of the art results across different transfer tasks, it’s not clear that our models made use of the semantic relation between sentences, thus leaving room for further improvements.</abstract>
<identifier type="citekey">sileo-etal-2019-mining</identifier>
<identifier type="doi">10.18653/v1/N19-1351</identifier>
<location>
<url>https://aclanthology.org/N19-1351</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>3477</start>
<end>3486</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mining Discourse Markers for Unsupervised Sentence Representation Learning
%A Sileo, Damien
%A Van De Cruys, Tim
%A Pradel, Camille
%A Muller, Philippe
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F sileo-etal-2019-mining
%X Current state of the art systems in NLP heavily rely on manually annotated datasets, which are expensive to construct. Very little work adequately exploits unannotated data – such as discourse markers between sentences – mainly because of data sparseness and ineffective extraction methods. In the present work, we propose a method to automatically discover sentence pairs with relevant discourse markers, and apply it to massive amounts of data. Our resulting dataset contains 174 discourse markers with at least 10k examples each, even for rare markers such as “coincidentally” or “amazingly”. We use the resulting data as supervision for learning transferable sentence embeddings. In addition, we show that even though sentence representation learning through prediction of discourse marker yields state of the art results across different transfer tasks, it’s not clear that our models made use of the semantic relation between sentences, thus leaving room for further improvements.
%R 10.18653/v1/N19-1351
%U https://aclanthology.org/N19-1351
%U https://doi.org/10.18653/v1/N19-1351
%P 3477-3486
Markdown (Informal)
[Mining Discourse Markers for Unsupervised Sentence Representation Learning](https://aclanthology.org/N19-1351) (Sileo et al., NAACL 2019)
ACL
- Damien Sileo, Tim Van De Cruys, Camille Pradel, and Philippe Muller. 2019. Mining Discourse Markers for Unsupervised Sentence Representation Learning. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3477–3486, Minneapolis, Minnesota. Association for Computational Linguistics.