@inproceedings{zopf-etal-2018-scores,
title = "Which Scores to Predict in Sentence Regression for Text Summarization?",
author = {Zopf, Markus and
Loza Menc{\'\i}a, Eneldo and
F{\"u}rnkranz, Johannes},
editor = "Walker, Marilyn and
Ji, Heng and
Stent, Amanda",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-1161",
doi = "10.18653/v1/N18-1161",
pages = "1782--1791",
abstract = "The task of automatic text summarization is to generate a short text that summarizes the most important information in a given set of documents. Sentence regression is an emerging branch in automatic text summarizations. Its key idea is to estimate the importance of information via learned utility scores for individual sentences. These scores are then used for selecting sentences from the source documents, typically according to a greedy selection strategy. Recently proposed state-of-the-art models learn to predict ROUGE recall scores of individual sentences, which seems reasonable since the final summaries are evaluated according to ROUGE recall. In this paper, we show in extensive experiments that following this intuition leads to suboptimal results and that learning to predict ROUGE precision scores leads to better results. The crucial difference is to aim not at covering as much information as possible but at wasting as little space as possible in every greedy step.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zopf-etal-2018-scores">
<titleInfo>
<title>Which Scores to Predict in Sentence Regression for Text Summarization?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Zopf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eneldo</namePart>
<namePart type="family">Loza Mencía</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Fürnkranz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marilyn</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Stent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The task of automatic text summarization is to generate a short text that summarizes the most important information in a given set of documents. Sentence regression is an emerging branch in automatic text summarizations. Its key idea is to estimate the importance of information via learned utility scores for individual sentences. These scores are then used for selecting sentences from the source documents, typically according to a greedy selection strategy. Recently proposed state-of-the-art models learn to predict ROUGE recall scores of individual sentences, which seems reasonable since the final summaries are evaluated according to ROUGE recall. In this paper, we show in extensive experiments that following this intuition leads to suboptimal results and that learning to predict ROUGE precision scores leads to better results. The crucial difference is to aim not at covering as much information as possible but at wasting as little space as possible in every greedy step.</abstract>
<identifier type="citekey">zopf-etal-2018-scores</identifier>
<identifier type="doi">10.18653/v1/N18-1161</identifier>
<location>
<url>https://aclanthology.org/N18-1161</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>1782</start>
<end>1791</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Which Scores to Predict in Sentence Regression for Text Summarization?
%A Zopf, Markus
%A Loza Mencía, Eneldo
%A Fürnkranz, Johannes
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F zopf-etal-2018-scores
%X The task of automatic text summarization is to generate a short text that summarizes the most important information in a given set of documents. Sentence regression is an emerging branch in automatic text summarizations. Its key idea is to estimate the importance of information via learned utility scores for individual sentences. These scores are then used for selecting sentences from the source documents, typically according to a greedy selection strategy. Recently proposed state-of-the-art models learn to predict ROUGE recall scores of individual sentences, which seems reasonable since the final summaries are evaluated according to ROUGE recall. In this paper, we show in extensive experiments that following this intuition leads to suboptimal results and that learning to predict ROUGE precision scores leads to better results. The crucial difference is to aim not at covering as much information as possible but at wasting as little space as possible in every greedy step.
%R 10.18653/v1/N18-1161
%U https://aclanthology.org/N18-1161
%U https://doi.org/10.18653/v1/N18-1161
%P 1782-1791
Markdown (Informal)
[Which Scores to Predict in Sentence Regression for Text Summarization?](https://aclanthology.org/N18-1161) (Zopf et al., NAACL 2018)
ACL
- Markus Zopf, Eneldo Loza Mencía, and Johannes Fürnkranz. 2018. Which Scores to Predict in Sentence Regression for Text Summarization?. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1782–1791, New Orleans, Louisiana. Association for Computational Linguistics.