@inproceedings{wang-etal-2024-information,
title = "An Information-Theoretic Approach to Analyze {NLP} Classification Tasks",
author = "Wang, Luran and
Gales, Mark and
Raina, Vatsal",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.32",
pages = "530--551",
abstract = "Understanding the contribution of the inputs on the output is useful across many tasks. This work provides an information-theoretic framework to analyse the influence of inputs for text classification tasks. Natural language processing (NLP) tasks take either a single or multiple text elements to predict an output variable. Each text element has two components: the semantic meaning and a linguistic realization. Multiple-choice reading comprehension (MCRC) and sentiment classification (SC) are selected to showcase the framework. For MCRC, it is found that the relative context influence on the output reduces on more challenging datasets. In particular, more challenging contexts allows greater variation in the question complexity. Hence, test creators need to carefully consider the choice of the context when designing multiple-choice questions for assessment. For SC, it is found the semantic meaning of the input dominates compared to its linguistic realization when determining the sentiment. The framework is made available at: https://github.com/WangLuran/nlp-element-influence.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-information">
<titleInfo>
<title>An Information-Theoretic Approach to Analyze NLP Classification Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luran</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Gales</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vatsal</namePart>
<namePart type="family">Raina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Understanding the contribution of the inputs on the output is useful across many tasks. This work provides an information-theoretic framework to analyse the influence of inputs for text classification tasks. Natural language processing (NLP) tasks take either a single or multiple text elements to predict an output variable. Each text element has two components: the semantic meaning and a linguistic realization. Multiple-choice reading comprehension (MCRC) and sentiment classification (SC) are selected to showcase the framework. For MCRC, it is found that the relative context influence on the output reduces on more challenging datasets. In particular, more challenging contexts allows greater variation in the question complexity. Hence, test creators need to carefully consider the choice of the context when designing multiple-choice questions for assessment. For SC, it is found the semantic meaning of the input dominates compared to its linguistic realization when determining the sentiment. The framework is made available at: https://github.com/WangLuran/nlp-element-influence.</abstract>
<identifier type="citekey">wang-etal-2024-information</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.32</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>530</start>
<end>551</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Information-Theoretic Approach to Analyze NLP Classification Tasks
%A Wang, Luran
%A Gales, Mark
%A Raina, Vatsal
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wang-etal-2024-information
%X Understanding the contribution of the inputs on the output is useful across many tasks. This work provides an information-theoretic framework to analyse the influence of inputs for text classification tasks. Natural language processing (NLP) tasks take either a single or multiple text elements to predict an output variable. Each text element has two components: the semantic meaning and a linguistic realization. Multiple-choice reading comprehension (MCRC) and sentiment classification (SC) are selected to showcase the framework. For MCRC, it is found that the relative context influence on the output reduces on more challenging datasets. In particular, more challenging contexts allows greater variation in the question complexity. Hence, test creators need to carefully consider the choice of the context when designing multiple-choice questions for assessment. For SC, it is found the semantic meaning of the input dominates compared to its linguistic realization when determining the sentiment. The framework is made available at: https://github.com/WangLuran/nlp-element-influence.
%U https://aclanthology.org/2024.acl-long.32
%P 530-551
Markdown (Informal)
[An Information-Theoretic Approach to Analyze NLP Classification Tasks](https://aclanthology.org/2024.acl-long.32) (Wang et al., ACL 2024)
ACL