@inproceedings{shichel-etal-2021-measured,
title = "With Measured Words: Simple Sentence Selection for Black-Box Optimization of Sentence Compression Algorithms",
author = "Shichel, Yotam and
Kalech, Meir and
Tsur, Oren",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.139",
doi = "10.18653/v1/2021.eacl-main.139",
pages = "1625--1634",
abstract = "Sentence Compression is the task of generating a shorter, yet grammatical, version of a given sentence, preserving the essence of the original sentence. This paper proposes a Black-Box Optimizer for Compression (B-BOC): given a black-box compression algorithm and assuming not all sentences need be compressed {--} find the best candidates for compression in order to maximize both compression rate and quality. Given a required compression ratio, we consider two scenarios: (i) single-sentence compression, and (ii) sentences-sequence compression. In the first scenario our optimizer is trained to predict how well each sentence could be compressed while meeting the specified ratio requirement. In the latter, the desired compression ratio is applied to a sequence of sentences (e.g., a paragraph) as a whole, rather than on each individual sentence. To achieve that we use B-BOC to assign an optimal compression ratio to each sentence, then cast it as a Knapsack problem which we solve using bounded dynamic programming. We evaluate B-BOC on both scenarios on three datasets, demonstrating that our optimizer improves both accuracy and Rouge-F1-score compared to direct application of other compression algorithms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shichel-etal-2021-measured">
<titleInfo>
<title>With Measured Words: Simple Sentence Selection for Black-Box Optimization of Sentence Compression Algorithms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yotam</namePart>
<namePart type="family">Shichel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meir</namePart>
<namePart type="family">Kalech</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oren</namePart>
<namePart type="family">Tsur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</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>Sentence Compression is the task of generating a shorter, yet grammatical, version of a given sentence, preserving the essence of the original sentence. This paper proposes a Black-Box Optimizer for Compression (B-BOC): given a black-box compression algorithm and assuming not all sentences need be compressed – find the best candidates for compression in order to maximize both compression rate and quality. Given a required compression ratio, we consider two scenarios: (i) single-sentence compression, and (ii) sentences-sequence compression. In the first scenario our optimizer is trained to predict how well each sentence could be compressed while meeting the specified ratio requirement. In the latter, the desired compression ratio is applied to a sequence of sentences (e.g., a paragraph) as a whole, rather than on each individual sentence. To achieve that we use B-BOC to assign an optimal compression ratio to each sentence, then cast it as a Knapsack problem which we solve using bounded dynamic programming. We evaluate B-BOC on both scenarios on three datasets, demonstrating that our optimizer improves both accuracy and Rouge-F1-score compared to direct application of other compression algorithms.</abstract>
<identifier type="citekey">shichel-etal-2021-measured</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.139</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.139</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>1625</start>
<end>1634</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T With Measured Words: Simple Sentence Selection for Black-Box Optimization of Sentence Compression Algorithms
%A Shichel, Yotam
%A Kalech, Meir
%A Tsur, Oren
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F shichel-etal-2021-measured
%X Sentence Compression is the task of generating a shorter, yet grammatical, version of a given sentence, preserving the essence of the original sentence. This paper proposes a Black-Box Optimizer for Compression (B-BOC): given a black-box compression algorithm and assuming not all sentences need be compressed – find the best candidates for compression in order to maximize both compression rate and quality. Given a required compression ratio, we consider two scenarios: (i) single-sentence compression, and (ii) sentences-sequence compression. In the first scenario our optimizer is trained to predict how well each sentence could be compressed while meeting the specified ratio requirement. In the latter, the desired compression ratio is applied to a sequence of sentences (e.g., a paragraph) as a whole, rather than on each individual sentence. To achieve that we use B-BOC to assign an optimal compression ratio to each sentence, then cast it as a Knapsack problem which we solve using bounded dynamic programming. We evaluate B-BOC on both scenarios on three datasets, demonstrating that our optimizer improves both accuracy and Rouge-F1-score compared to direct application of other compression algorithms.
%R 10.18653/v1/2021.eacl-main.139
%U https://aclanthology.org/2021.eacl-main.139
%U https://doi.org/10.18653/v1/2021.eacl-main.139
%P 1625-1634
Markdown (Informal)
[With Measured Words: Simple Sentence Selection for Black-Box Optimization of Sentence Compression Algorithms](https://aclanthology.org/2021.eacl-main.139) (Shichel et al., EACL 2021)
ACL