@inproceedings{faruqui-etal-2018-wikiatomicedits,
title = "{W}iki{A}tomic{E}dits: A Multilingual Corpus of {W}ikipedia Edits for Modeling Language and Discourse",
author = "Faruqui, Manaal and
Pavlick, Ellie and
Tenney, Ian and
Das, Dipanjan",
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/D18-1028",
doi = "10.18653/v1/D18-1028",
pages = "305--315",
abstract = "We release a corpus of 43 million atomic edits across 8 languages. These edits are mined from Wikipedia edit history and consist of instances in which a human editor has inserted a single contiguous phrase into, or deleted a single contiguous phrase from, an existing sentence. We use the collected data to show that the language generated during editing differs from the language that we observe in standard corpora, and that models trained on edits encode different aspects of semantics and discourse than models trained on raw text. We release the full corpus as a resource to aid ongoing research in semantics, discourse, and representation learning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="faruqui-etal-2018-wikiatomicedits">
<titleInfo>
<title>WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manaal</namePart>
<namePart type="family">Faruqui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellie</namePart>
<namePart type="family">Pavlick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="family">Tenney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipanjan</namePart>
<namePart type="family">Das</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>We release a corpus of 43 million atomic edits across 8 languages. These edits are mined from Wikipedia edit history and consist of instances in which a human editor has inserted a single contiguous phrase into, or deleted a single contiguous phrase from, an existing sentence. We use the collected data to show that the language generated during editing differs from the language that we observe in standard corpora, and that models trained on edits encode different aspects of semantics and discourse than models trained on raw text. We release the full corpus as a resource to aid ongoing research in semantics, discourse, and representation learning.</abstract>
<identifier type="citekey">faruqui-etal-2018-wikiatomicedits</identifier>
<identifier type="doi">10.18653/v1/D18-1028</identifier>
<location>
<url>https://aclanthology.org/D18-1028</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>305</start>
<end>315</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse
%A Faruqui, Manaal
%A Pavlick, Ellie
%A Tenney, Ian
%A Das, Dipanjan
%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 faruqui-etal-2018-wikiatomicedits
%X We release a corpus of 43 million atomic edits across 8 languages. These edits are mined from Wikipedia edit history and consist of instances in which a human editor has inserted a single contiguous phrase into, or deleted a single contiguous phrase from, an existing sentence. We use the collected data to show that the language generated during editing differs from the language that we observe in standard corpora, and that models trained on edits encode different aspects of semantics and discourse than models trained on raw text. We release the full corpus as a resource to aid ongoing research in semantics, discourse, and representation learning.
%R 10.18653/v1/D18-1028
%U https://aclanthology.org/D18-1028
%U https://doi.org/10.18653/v1/D18-1028
%P 305-315
Markdown (Informal)
[WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse](https://aclanthology.org/D18-1028) (Faruqui et al., EMNLP 2018)
ACL