@inproceedings{sarkhel-etal-2020-interpretable,
title = "Interpretable Multi-headed Attention for Abstractive Summarization at Controllable Lengths",
author = "Sarkhel, Ritesh and
Keymanesh, Moniba and
Nandi, Arnab and
Parthasarathy, Srinivasan",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.606",
doi = "10.18653/v1/2020.coling-main.606",
pages = "6871--6882",
abstract = "Abstractive summarization at controllable lengths is a challenging task in natural language processing. It is even more challenging for domains where limited training data is available or scenarios in which the length of the summary is not known beforehand. At the same time, when it comes to trusting machine-generated summaries, explaining how a summary was constructed in human-understandable terms may be critical. We propose Multi-level Summarizer (MLS), a supervised method to construct abstractive summaries of a text document at controllable lengths. The key enabler of our method is an interpretable multi-headed attention mechanism that computes attention distribution over an input document using an array of timestep independent semantic kernels. Each kernel optimizes a human-interpretable syntactic or semantic property. Exhaustive experiments on two low-resource datasets in English show that MLS outperforms strong baselines by up to 14.70{\%} in the METEOR score. Human evaluation of the summaries also suggests that they capture the key concepts of the document at various length-budgets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sarkhel-etal-2020-interpretable">
<titleInfo>
<title>Interpretable Multi-headed Attention for Abstractive Summarization at Controllable Lengths</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Sarkhel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moniba</namePart>
<namePart type="family">Keymanesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arnab</namePart>
<namePart type="family">Nandi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srinivasan</namePart>
<namePart type="family">Parthasarathy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Abstractive summarization at controllable lengths is a challenging task in natural language processing. It is even more challenging for domains where limited training data is available or scenarios in which the length of the summary is not known beforehand. At the same time, when it comes to trusting machine-generated summaries, explaining how a summary was constructed in human-understandable terms may be critical. We propose Multi-level Summarizer (MLS), a supervised method to construct abstractive summaries of a text document at controllable lengths. The key enabler of our method is an interpretable multi-headed attention mechanism that computes attention distribution over an input document using an array of timestep independent semantic kernels. Each kernel optimizes a human-interpretable syntactic or semantic property. Exhaustive experiments on two low-resource datasets in English show that MLS outperforms strong baselines by up to 14.70% in the METEOR score. Human evaluation of the summaries also suggests that they capture the key concepts of the document at various length-budgets.</abstract>
<identifier type="citekey">sarkhel-etal-2020-interpretable</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.606</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.606</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>6871</start>
<end>6882</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interpretable Multi-headed Attention for Abstractive Summarization at Controllable Lengths
%A Sarkhel, Ritesh
%A Keymanesh, Moniba
%A Nandi, Arnab
%A Parthasarathy, Srinivasan
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F sarkhel-etal-2020-interpretable
%X Abstractive summarization at controllable lengths is a challenging task in natural language processing. It is even more challenging for domains where limited training data is available or scenarios in which the length of the summary is not known beforehand. At the same time, when it comes to trusting machine-generated summaries, explaining how a summary was constructed in human-understandable terms may be critical. We propose Multi-level Summarizer (MLS), a supervised method to construct abstractive summaries of a text document at controllable lengths. The key enabler of our method is an interpretable multi-headed attention mechanism that computes attention distribution over an input document using an array of timestep independent semantic kernels. Each kernel optimizes a human-interpretable syntactic or semantic property. Exhaustive experiments on two low-resource datasets in English show that MLS outperforms strong baselines by up to 14.70% in the METEOR score. Human evaluation of the summaries also suggests that they capture the key concepts of the document at various length-budgets.
%R 10.18653/v1/2020.coling-main.606
%U https://aclanthology.org/2020.coling-main.606
%U https://doi.org/10.18653/v1/2020.coling-main.606
%P 6871-6882
Markdown (Informal)
[Interpretable Multi-headed Attention for Abstractive Summarization at Controllable Lengths](https://aclanthology.org/2020.coling-main.606) (Sarkhel et al., COLING 2020)
ACL