@inproceedings{guo-etal-2024-personalized,
title = "Personalized Jargon Identification for Enhanced Interdisciplinary Communication",
author = "Guo, Yue and
Chang, Joseph Chee and
Antoniak, Maria and
Bransom, Erin and
Cohen, Trevor and
Wang, Lucy and
August, Tal",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.255",
doi = "10.18653/v1/2024.naacl-long.255",
pages = "4535--4550",
abstract = "Scientific jargon can confuse researchers when they read materials from other domains. Identifying and translating jargon for individual researchers could speed up research, but current methods of jargon identification mainly use corpus-level familiarity indicators rather than modeling researcher-specific needs, which can vary greatly based on each researcher{'}s background. We collect a dataset of over 10K term familiarity annotations from 11 computer science researchers for terms drawn from 100 paper abstracts. Analysis of this data reveals that jargon familiarity and information needs vary widely across annotators, even within the same sub-domain (e.g., NLP). We investigate features representing domain, subdomain, and individual knowledge to predict individual jargon familiarity. We compare supervised and prompt-based approaches, finding that prompt-based methods using information about the individual researcher (e.g., personal publications, self-defined subfield of research) yield the highest accuracy, though the task remains difficult and supervised approaches have lower false positive rates. This research offers insights into features and methods for the novel task of integrating personal data into scientific jargon identification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2024-personalized">
<titleInfo>
<title>Personalized Jargon Identification for Enhanced Interdisciplinary Communication</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="given">Chee</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Antoniak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erin</namePart>
<namePart type="family">Bransom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucy</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">August</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Scientific jargon can confuse researchers when they read materials from other domains. Identifying and translating jargon for individual researchers could speed up research, but current methods of jargon identification mainly use corpus-level familiarity indicators rather than modeling researcher-specific needs, which can vary greatly based on each researcher’s background. We collect a dataset of over 10K term familiarity annotations from 11 computer science researchers for terms drawn from 100 paper abstracts. Analysis of this data reveals that jargon familiarity and information needs vary widely across annotators, even within the same sub-domain (e.g., NLP). We investigate features representing domain, subdomain, and individual knowledge to predict individual jargon familiarity. We compare supervised and prompt-based approaches, finding that prompt-based methods using information about the individual researcher (e.g., personal publications, self-defined subfield of research) yield the highest accuracy, though the task remains difficult and supervised approaches have lower false positive rates. This research offers insights into features and methods for the novel task of integrating personal data into scientific jargon identification.</abstract>
<identifier type="citekey">guo-etal-2024-personalized</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.255</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.255</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>4535</start>
<end>4550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Personalized Jargon Identification for Enhanced Interdisciplinary Communication
%A Guo, Yue
%A Chang, Joseph Chee
%A Antoniak, Maria
%A Bransom, Erin
%A Cohen, Trevor
%A Wang, Lucy
%A August, Tal
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F guo-etal-2024-personalized
%X Scientific jargon can confuse researchers when they read materials from other domains. Identifying and translating jargon for individual researchers could speed up research, but current methods of jargon identification mainly use corpus-level familiarity indicators rather than modeling researcher-specific needs, which can vary greatly based on each researcher’s background. We collect a dataset of over 10K term familiarity annotations from 11 computer science researchers for terms drawn from 100 paper abstracts. Analysis of this data reveals that jargon familiarity and information needs vary widely across annotators, even within the same sub-domain (e.g., NLP). We investigate features representing domain, subdomain, and individual knowledge to predict individual jargon familiarity. We compare supervised and prompt-based approaches, finding that prompt-based methods using information about the individual researcher (e.g., personal publications, self-defined subfield of research) yield the highest accuracy, though the task remains difficult and supervised approaches have lower false positive rates. This research offers insights into features and methods for the novel task of integrating personal data into scientific jargon identification.
%R 10.18653/v1/2024.naacl-long.255
%U https://aclanthology.org/2024.naacl-long.255
%U https://doi.org/10.18653/v1/2024.naacl-long.255
%P 4535-4550
Markdown (Informal)
[Personalized Jargon Identification for Enhanced Interdisciplinary Communication](https://aclanthology.org/2024.naacl-long.255) (Guo et al., NAACL 2024)
ACL
- Yue Guo, Joseph Chee Chang, Maria Antoniak, Erin Bransom, Trevor Cohen, Lucy Wang, and Tal August. 2024. Personalized Jargon Identification for Enhanced Interdisciplinary Communication. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 4535–4550, Mexico City, Mexico. Association for Computational Linguistics.