@inproceedings{sarkar-etal-2019-stre,
title = "{S}t{RE}: Self Attentive Edit Quality Prediction in {W}ikipedia",
author = "Sarkar, Soumya and
Reddy, Bhanu Prakash and
Sikdar, Sandipan and
Mukherjee, Animesh",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1387",
doi = "10.18653/v1/P19-1387",
pages = "3962--3972",
abstract = "Wikipedia can easily be justified as a behemoth, considering the sheer volume of content that is added or removed every minute to its several projects. This creates an immense scope, in the field of natural language processing toward developing automated tools for content moderation and review. In this paper we propose Self Attentive Revision Encoder (StRE) which leverages orthographic similarity of lexical units toward predicting the quality of new edits. In contrast to existing propositions which primarily employ features like page reputation, editor activity or rule based heuristics, we utilize the textual content of the edits which, we believe contains superior signatures of their quality. More specifically, we deploy deep encoders to generate representations of the edits from its text content, which we then leverage to infer quality. We further contribute a novel dataset containing ∼ 21M revisions across 32K Wikipedia pages and demonstrate that StRE outperforms existing methods by a significant margin {--} at least 17{\%} and at most 103{\%}. Our pre-trained model achieves such result after retraining on a set as small as 20{\%} of the edits in a wikipage. This, to the best of our knowledge, is also the first attempt towards employing deep language models to the enormous domain of automated content moderation and review in Wikipedia.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sarkar-etal-2019-stre">
<titleInfo>
<title>StRE: Self Attentive Edit Quality Prediction in Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Soumya</namePart>
<namePart type="family">Sarkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhanu</namePart>
<namePart type="given">Prakash</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandipan</namePart>
<namePart type="family">Sikdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Animesh</namePart>
<namePart type="family">Mukherjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Wikipedia can easily be justified as a behemoth, considering the sheer volume of content that is added or removed every minute to its several projects. This creates an immense scope, in the field of natural language processing toward developing automated tools for content moderation and review. In this paper we propose Self Attentive Revision Encoder (StRE) which leverages orthographic similarity of lexical units toward predicting the quality of new edits. In contrast to existing propositions which primarily employ features like page reputation, editor activity or rule based heuristics, we utilize the textual content of the edits which, we believe contains superior signatures of their quality. More specifically, we deploy deep encoders to generate representations of the edits from its text content, which we then leverage to infer quality. We further contribute a novel dataset containing ∼ 21M revisions across 32K Wikipedia pages and demonstrate that StRE outperforms existing methods by a significant margin – at least 17% and at most 103%. Our pre-trained model achieves such result after retraining on a set as small as 20% of the edits in a wikipage. This, to the best of our knowledge, is also the first attempt towards employing deep language models to the enormous domain of automated content moderation and review in Wikipedia.</abstract>
<identifier type="citekey">sarkar-etal-2019-stre</identifier>
<identifier type="doi">10.18653/v1/P19-1387</identifier>
<location>
<url>https://aclanthology.org/P19-1387</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>3962</start>
<end>3972</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T StRE: Self Attentive Edit Quality Prediction in Wikipedia
%A Sarkar, Soumya
%A Reddy, Bhanu Prakash
%A Sikdar, Sandipan
%A Mukherjee, Animesh
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F sarkar-etal-2019-stre
%X Wikipedia can easily be justified as a behemoth, considering the sheer volume of content that is added or removed every minute to its several projects. This creates an immense scope, in the field of natural language processing toward developing automated tools for content moderation and review. In this paper we propose Self Attentive Revision Encoder (StRE) which leverages orthographic similarity of lexical units toward predicting the quality of new edits. In contrast to existing propositions which primarily employ features like page reputation, editor activity or rule based heuristics, we utilize the textual content of the edits which, we believe contains superior signatures of their quality. More specifically, we deploy deep encoders to generate representations of the edits from its text content, which we then leverage to infer quality. We further contribute a novel dataset containing ∼ 21M revisions across 32K Wikipedia pages and demonstrate that StRE outperforms existing methods by a significant margin – at least 17% and at most 103%. Our pre-trained model achieves such result after retraining on a set as small as 20% of the edits in a wikipage. This, to the best of our knowledge, is also the first attempt towards employing deep language models to the enormous domain of automated content moderation and review in Wikipedia.
%R 10.18653/v1/P19-1387
%U https://aclanthology.org/P19-1387
%U https://doi.org/10.18653/v1/P19-1387
%P 3962-3972
Markdown (Informal)
[StRE: Self Attentive Edit Quality Prediction in Wikipedia](https://aclanthology.org/P19-1387) (Sarkar et al., ACL 2019)
ACL
- Soumya Sarkar, Bhanu Prakash Reddy, Sandipan Sikdar, and Animesh Mukherjee. 2019. StRE: Self Attentive Edit Quality Prediction in Wikipedia. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3962–3972, Florence, Italy. Association for Computational Linguistics.