@inproceedings{west-etal-2019-bottlesum,
title = "{B}ottle{S}um: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle",
author = "West, Peter and
Holtzman, Ari and
Buys, Jan and
Choi, Yejin",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1389",
doi = "10.18653/v1/D19-1389",
pages = "3752--3761",
abstract = "The principle of the Information Bottleneck (Tishby et al., 1999) produces a summary of information X optimized to predict some other relevant information Y. In this paper, we propose a novel approach to unsupervised sentence summarization by mapping the Information Bottleneck principle to a conditional language modelling objective: given a sentence, our approach seeks a compressed sentence that can best predict the next sentence. Our iterative algorithm under the Information Bottleneck objective searches gradually shorter subsequences of the given sentence while maximizing the probability of the next sentence conditioned on the summary. Using only pretrained language models with no direct supervision, our approach can efficiently perform extractive sentence summarization over a large corpus. Building on our unsupervised extractive summarization, we also present a new approach to self-supervised abstractive summarization, where a transformer-based language model is trained on the output summaries of our unsupervised method. Empirical results demonstrate that our extractive method outperforms other unsupervised models on multiple automatic metrics. In addition, we find that our self-supervised abstractive model outperforms unsupervised baselines (including our own) by human evaluation along multiple attributes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="west-etal-2019-bottlesum">
<titleInfo>
<title>BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">West</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ari</namePart>
<namePart type="family">Holtzman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Buys</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yejin</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The principle of the Information Bottleneck (Tishby et al., 1999) produces a summary of information X optimized to predict some other relevant information Y. In this paper, we propose a novel approach to unsupervised sentence summarization by mapping the Information Bottleneck principle to a conditional language modelling objective: given a sentence, our approach seeks a compressed sentence that can best predict the next sentence. Our iterative algorithm under the Information Bottleneck objective searches gradually shorter subsequences of the given sentence while maximizing the probability of the next sentence conditioned on the summary. Using only pretrained language models with no direct supervision, our approach can efficiently perform extractive sentence summarization over a large corpus. Building on our unsupervised extractive summarization, we also present a new approach to self-supervised abstractive summarization, where a transformer-based language model is trained on the output summaries of our unsupervised method. Empirical results demonstrate that our extractive method outperforms other unsupervised models on multiple automatic metrics. In addition, we find that our self-supervised abstractive model outperforms unsupervised baselines (including our own) by human evaluation along multiple attributes.</abstract>
<identifier type="citekey">west-etal-2019-bottlesum</identifier>
<identifier type="doi">10.18653/v1/D19-1389</identifier>
<location>
<url>https://aclanthology.org/D19-1389</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>3752</start>
<end>3761</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle
%A West, Peter
%A Holtzman, Ari
%A Buys, Jan
%A Choi, Yejin
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F west-etal-2019-bottlesum
%X The principle of the Information Bottleneck (Tishby et al., 1999) produces a summary of information X optimized to predict some other relevant information Y. In this paper, we propose a novel approach to unsupervised sentence summarization by mapping the Information Bottleneck principle to a conditional language modelling objective: given a sentence, our approach seeks a compressed sentence that can best predict the next sentence. Our iterative algorithm under the Information Bottleneck objective searches gradually shorter subsequences of the given sentence while maximizing the probability of the next sentence conditioned on the summary. Using only pretrained language models with no direct supervision, our approach can efficiently perform extractive sentence summarization over a large corpus. Building on our unsupervised extractive summarization, we also present a new approach to self-supervised abstractive summarization, where a transformer-based language model is trained on the output summaries of our unsupervised method. Empirical results demonstrate that our extractive method outperforms other unsupervised models on multiple automatic metrics. In addition, we find that our self-supervised abstractive model outperforms unsupervised baselines (including our own) by human evaluation along multiple attributes.
%R 10.18653/v1/D19-1389
%U https://aclanthology.org/D19-1389
%U https://doi.org/10.18653/v1/D19-1389
%P 3752-3761
Markdown (Informal)
[BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle](https://aclanthology.org/D19-1389) (West et al., EMNLP-IJCNLP 2019)
ACL