@inproceedings{patel-etal-2021-game,
title = "Game-theoretic Vocabulary Selection via the Shapley Value and Banzhaf Index",
author = "Patel, Roma and
Garnelo, Marta and
Gemp, Ian and
Dyer, Chris and
Bachrach, Yoram",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.223",
doi = "10.18653/v1/2021.naacl-main.223",
pages = "2789--2798",
abstract = "The input vocabulary and the representations learned are crucial to the performance of neural NLP models. Using the full vocabulary results in less explainable and more memory intensive models, with the embedding layer often constituting the majority of model parameters. It is thus common to use a smaller vocabulary to lower memory requirements and construct more interpertable models. We propose a vocabulary selection method that views words as members of a team trying to maximize the model{'}s performance. We apply power indices from cooperative game theory, including the Shapley value and Banzhaf index, that measure the relative importance of individual team members in accomplishing a joint task. We approximately compute these indices to identify the most influential words. Our empirical evaluation examines multiple NLP tasks, including sentence and document classification, question answering and textual entailment. We compare to baselines that select words based on frequency, TF-IDF and regression coefficients under L1 regularization, and show that this game-theoretic vocabulary selection outperforms all baseline on a range of different tasks and datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="patel-etal-2021-game">
<titleInfo>
<title>Game-theoretic Vocabulary Selection via the Shapley Value and Banzhaf Index</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roma</namePart>
<namePart type="family">Patel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Garnelo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="family">Gemp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Dyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoram</namePart>
<namePart type="family">Bachrach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>The input vocabulary and the representations learned are crucial to the performance of neural NLP models. Using the full vocabulary results in less explainable and more memory intensive models, with the embedding layer often constituting the majority of model parameters. It is thus common to use a smaller vocabulary to lower memory requirements and construct more interpertable models. We propose a vocabulary selection method that views words as members of a team trying to maximize the model’s performance. We apply power indices from cooperative game theory, including the Shapley value and Banzhaf index, that measure the relative importance of individual team members in accomplishing a joint task. We approximately compute these indices to identify the most influential words. Our empirical evaluation examines multiple NLP tasks, including sentence and document classification, question answering and textual entailment. We compare to baselines that select words based on frequency, TF-IDF and regression coefficients under L1 regularization, and show that this game-theoretic vocabulary selection outperforms all baseline on a range of different tasks and datasets.</abstract>
<identifier type="citekey">patel-etal-2021-game</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.223</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.223</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>2789</start>
<end>2798</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Game-theoretic Vocabulary Selection via the Shapley Value and Banzhaf Index
%A Patel, Roma
%A Garnelo, Marta
%A Gemp, Ian
%A Dyer, Chris
%A Bachrach, Yoram
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F patel-etal-2021-game
%X The input vocabulary and the representations learned are crucial to the performance of neural NLP models. Using the full vocabulary results in less explainable and more memory intensive models, with the embedding layer often constituting the majority of model parameters. It is thus common to use a smaller vocabulary to lower memory requirements and construct more interpertable models. We propose a vocabulary selection method that views words as members of a team trying to maximize the model’s performance. We apply power indices from cooperative game theory, including the Shapley value and Banzhaf index, that measure the relative importance of individual team members in accomplishing a joint task. We approximately compute these indices to identify the most influential words. Our empirical evaluation examines multiple NLP tasks, including sentence and document classification, question answering and textual entailment. We compare to baselines that select words based on frequency, TF-IDF and regression coefficients under L1 regularization, and show that this game-theoretic vocabulary selection outperforms all baseline on a range of different tasks and datasets.
%R 10.18653/v1/2021.naacl-main.223
%U https://aclanthology.org/2021.naacl-main.223
%U https://doi.org/10.18653/v1/2021.naacl-main.223
%P 2789-2798
Markdown (Informal)
[Game-theoretic Vocabulary Selection via the Shapley Value and Banzhaf Index](https://aclanthology.org/2021.naacl-main.223) (Patel et al., NAACL 2021)
ACL