@inproceedings{geng-etal-2022-inducing,
title = "Inducing Generalizable and Interpretable Lexica",
author = "Geng, Yilin and
Wu, Zetian and
Santhosh, Roshan and
Srivastava, Tejas and
Ungar, Lyle and
Sedoc, Jo{\~a}o",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.325",
doi = "10.18653/v1/2022.findings-emnlp.325",
pages = "4430--4448",
abstract = "Lexica {--} words and associated scores {--} are widely used as simple, interpretable, generalizable language features to predict sentiment, emotions, mental health, and personality. They also provide insight into the psychological features behind those moods and traits. Such lexica, historically created by human experts, are valuable to linguists, psychologists, and social scientists, but they take years of refinement and have limited coverage. In this paper, we investigate how the lexica that provide psycholinguistic insights could be computationally induced and how they should be assessed. We identify generalizability and interpretability as two essential properties of such lexica. We induce lexica using both context-oblivious and context-aware approaches, compare their predictive performance both within the training corpus and across various corpora, and evaluate their quality using crowd-worker assessment. We find that lexica induced from context-oblivious models are more generalizable and interpretable than those from more accurate context-aware transformer models. In addition, lexicon scores can identify explanatory words more reliably than a high performing transformer with feature-importance measures like SHAP.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="geng-etal-2022-inducing">
<titleInfo>
<title>Inducing Generalizable and Interpretable Lexica</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yilin</namePart>
<namePart type="family">Geng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zetian</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roshan</namePart>
<namePart type="family">Santhosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tejas</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lyle</namePart>
<namePart type="family">Ungar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Lexica – words and associated scores – are widely used as simple, interpretable, generalizable language features to predict sentiment, emotions, mental health, and personality. They also provide insight into the psychological features behind those moods and traits. Such lexica, historically created by human experts, are valuable to linguists, psychologists, and social scientists, but they take years of refinement and have limited coverage. In this paper, we investigate how the lexica that provide psycholinguistic insights could be computationally induced and how they should be assessed. We identify generalizability and interpretability as two essential properties of such lexica. We induce lexica using both context-oblivious and context-aware approaches, compare their predictive performance both within the training corpus and across various corpora, and evaluate their quality using crowd-worker assessment. We find that lexica induced from context-oblivious models are more generalizable and interpretable than those from more accurate context-aware transformer models. In addition, lexicon scores can identify explanatory words more reliably than a high performing transformer with feature-importance measures like SHAP.</abstract>
<identifier type="citekey">geng-etal-2022-inducing</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.325</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.325</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>4430</start>
<end>4448</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Inducing Generalizable and Interpretable Lexica
%A Geng, Yilin
%A Wu, Zetian
%A Santhosh, Roshan
%A Srivastava, Tejas
%A Ungar, Lyle
%A Sedoc, João
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F geng-etal-2022-inducing
%X Lexica – words and associated scores – are widely used as simple, interpretable, generalizable language features to predict sentiment, emotions, mental health, and personality. They also provide insight into the psychological features behind those moods and traits. Such lexica, historically created by human experts, are valuable to linguists, psychologists, and social scientists, but they take years of refinement and have limited coverage. In this paper, we investigate how the lexica that provide psycholinguistic insights could be computationally induced and how they should be assessed. We identify generalizability and interpretability as two essential properties of such lexica. We induce lexica using both context-oblivious and context-aware approaches, compare their predictive performance both within the training corpus and across various corpora, and evaluate their quality using crowd-worker assessment. We find that lexica induced from context-oblivious models are more generalizable and interpretable than those from more accurate context-aware transformer models. In addition, lexicon scores can identify explanatory words more reliably than a high performing transformer with feature-importance measures like SHAP.
%R 10.18653/v1/2022.findings-emnlp.325
%U https://aclanthology.org/2022.findings-emnlp.325
%U https://doi.org/10.18653/v1/2022.findings-emnlp.325
%P 4430-4448
Markdown (Informal)
[Inducing Generalizable and Interpretable Lexica](https://aclanthology.org/2022.findings-emnlp.325) (Geng et al., Findings 2022)
ACL
- Yilin Geng, Zetian Wu, Roshan Santhosh, Tejas Srivastava, Lyle Ungar, and João Sedoc. 2022. Inducing Generalizable and Interpretable Lexica. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4430–4448, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.