@inproceedings{lin-morency-2023-sentecon,
title = "{S}ente{C}on: Leveraging Lexicons to Learn Human-Interpretable Language Representations",
author = "Lin, Victoria and
Morency, Louis-Philippe",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.264/",
doi = "10.18653/v1/2023.findings-acl.264",
pages = "4312--4331",
abstract = "Although deep language representations have become the dominant form of language featurization in recent years, in many settings it is important to understand a model`s decision-making process. This necessitates not only an interpretable model but also interpretable features. In particular, language must be featurized in a way that is interpretable while still characterizing the original text well. We present SenteCon, a method for introducing human interpretability in deep language representations. Given a passage of text, SenteCon encodes the text as a layer of interpretable categories in which each dimension corresponds to the relevance of a specific category. Our empirical evaluations indicate that encoding language with SenteCon provides high-level interpretability at little to no cost to predictive performance on downstream tasks. Moreover, we find that SenteCon outperforms existing interpretable language representations with respect to both its downstream performance and its agreement with human characterizations of the text."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-morency-2023-sentecon">
<titleInfo>
<title>SenteCon: Leveraging Lexicons to Learn Human-Interpretable Language Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louis-Philippe</namePart>
<namePart type="family">Morency</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although deep language representations have become the dominant form of language featurization in recent years, in many settings it is important to understand a model‘s decision-making process. This necessitates not only an interpretable model but also interpretable features. In particular, language must be featurized in a way that is interpretable while still characterizing the original text well. We present SenteCon, a method for introducing human interpretability in deep language representations. Given a passage of text, SenteCon encodes the text as a layer of interpretable categories in which each dimension corresponds to the relevance of a specific category. Our empirical evaluations indicate that encoding language with SenteCon provides high-level interpretability at little to no cost to predictive performance on downstream tasks. Moreover, we find that SenteCon outperforms existing interpretable language representations with respect to both its downstream performance and its agreement with human characterizations of the text.</abstract>
<identifier type="citekey">lin-morency-2023-sentecon</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.264</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.264/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>4312</start>
<end>4331</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SenteCon: Leveraging Lexicons to Learn Human-Interpretable Language Representations
%A Lin, Victoria
%A Morency, Louis-Philippe
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F lin-morency-2023-sentecon
%X Although deep language representations have become the dominant form of language featurization in recent years, in many settings it is important to understand a model‘s decision-making process. This necessitates not only an interpretable model but also interpretable features. In particular, language must be featurized in a way that is interpretable while still characterizing the original text well. We present SenteCon, a method for introducing human interpretability in deep language representations. Given a passage of text, SenteCon encodes the text as a layer of interpretable categories in which each dimension corresponds to the relevance of a specific category. Our empirical evaluations indicate that encoding language with SenteCon provides high-level interpretability at little to no cost to predictive performance on downstream tasks. Moreover, we find that SenteCon outperforms existing interpretable language representations with respect to both its downstream performance and its agreement with human characterizations of the text.
%R 10.18653/v1/2023.findings-acl.264
%U https://aclanthology.org/2023.findings-acl.264/
%U https://doi.org/10.18653/v1/2023.findings-acl.264
%P 4312-4331
Markdown (Informal)
[SenteCon: Leveraging Lexicons to Learn Human-Interpretable Language Representations](https://aclanthology.org/2023.findings-acl.264/) (Lin & Morency, Findings 2023)
ACL