@inproceedings{deutsch-roth-2020-sacrerouge,
title = "{S}acre{ROUGE}: An Open-Source Library for Using and Developing Summarization Evaluation Metrics",
author = "Deutsch, Daniel and
Roth, Dan",
editor = "Park, Eunjeong L. and
Hagiwara, Masato and
Milajevs, Dmitrijs and
Liu, Nelson F. and
Chauhan, Geeticka and
Tan, Liling",
booktitle = "Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlposs-1.17",
doi = "10.18653/v1/2020.nlposs-1.17",
pages = "120--125",
abstract = "We present SacreROUGE, an open-source library for using and developing summarization evaluation metrics. SacreROUGE removes many obstacles that researchers face when using or developing metrics: (1) The library provides Python wrappers around the official implementations of existing evaluation metrics so they share a common, easy-to-use interface; (2) it provides functionality to evaluate how well any metric implemented in the library correlates to human-annotated judgments, so no additional code needs to be written for a new evaluation metric; and (3) it includes scripts for loading datasets that contain human judgments so they can easily be used for evaluation. This work describes the design of the library, including the core Metric interface, the command-line API for evaluating summarization models and metrics, and the scripts to load and reformat publicly available datasets. The development of SacreROUGE is ongoing and open to contributions from the community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deutsch-roth-2020-sacrerouge">
<titleInfo>
<title>SacreROUGE: An Open-Source Library for Using and Developing Summarization Evaluation Metrics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Deutsch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Roth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eunjeong</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masato</namePart>
<namePart type="family">Hagiwara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitrijs</namePart>
<namePart type="family">Milajevs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nelson</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geeticka</namePart>
<namePart type="family">Chauhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liling</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present SacreROUGE, an open-source library for using and developing summarization evaluation metrics. SacreROUGE removes many obstacles that researchers face when using or developing metrics: (1) The library provides Python wrappers around the official implementations of existing evaluation metrics so they share a common, easy-to-use interface; (2) it provides functionality to evaluate how well any metric implemented in the library correlates to human-annotated judgments, so no additional code needs to be written for a new evaluation metric; and (3) it includes scripts for loading datasets that contain human judgments so they can easily be used for evaluation. This work describes the design of the library, including the core Metric interface, the command-line API for evaluating summarization models and metrics, and the scripts to load and reformat publicly available datasets. The development of SacreROUGE is ongoing and open to contributions from the community.</abstract>
<identifier type="citekey">deutsch-roth-2020-sacrerouge</identifier>
<identifier type="doi">10.18653/v1/2020.nlposs-1.17</identifier>
<location>
<url>https://aclanthology.org/2020.nlposs-1.17</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>120</start>
<end>125</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SacreROUGE: An Open-Source Library for Using and Developing Summarization Evaluation Metrics
%A Deutsch, Daniel
%A Roth, Dan
%Y Park, Eunjeong L.
%Y Hagiwara, Masato
%Y Milajevs, Dmitrijs
%Y Liu, Nelson F.
%Y Chauhan, Geeticka
%Y Tan, Liling
%S Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F deutsch-roth-2020-sacrerouge
%X We present SacreROUGE, an open-source library for using and developing summarization evaluation metrics. SacreROUGE removes many obstacles that researchers face when using or developing metrics: (1) The library provides Python wrappers around the official implementations of existing evaluation metrics so they share a common, easy-to-use interface; (2) it provides functionality to evaluate how well any metric implemented in the library correlates to human-annotated judgments, so no additional code needs to be written for a new evaluation metric; and (3) it includes scripts for loading datasets that contain human judgments so they can easily be used for evaluation. This work describes the design of the library, including the core Metric interface, the command-line API for evaluating summarization models and metrics, and the scripts to load and reformat publicly available datasets. The development of SacreROUGE is ongoing and open to contributions from the community.
%R 10.18653/v1/2020.nlposs-1.17
%U https://aclanthology.org/2020.nlposs-1.17
%U https://doi.org/10.18653/v1/2020.nlposs-1.17
%P 120-125
Markdown (Informal)
[SacreROUGE: An Open-Source Library for Using and Developing Summarization Evaluation Metrics](https://aclanthology.org/2020.nlposs-1.17) (Deutsch & Roth, NLPOSS 2020)
ACL