@inproceedings{huang-etal-2022-understanding,
title = "Understanding Jargon: Combining Extraction and Generation for Definition Modeling",
author = "Huang, Jie and
Shao, Hanyin and
Chang, Kevin Chen-Chuan and
Xiong, Jinjun and
Hwu, Wen-mei",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.266",
doi = "10.18653/v1/2022.emnlp-main.266",
pages = "3994--4004",
abstract = "Can machines know what twin prime is? From the composition of this phrase, machines may guess twin prime is a certain kind of prime, but it is still difficult to deduce exactly what twin stands for without additional knowledge. Here, twin prime is a jargon - a specialized term used by experts in a particular field. Explaining jargon is challenging since it usually requires domain knowledge to understand. Recently, there is an increasing interest in extracting and generating definitions of words automatically. However, existing approaches, either extraction or generation, perform poorly on jargon. In this paper, we propose to combine extraction and generation for jargon definition modeling: first extract self- and correlative definitional information of target jargon from the Web and then generate the final definitions by incorporating the extracted definitional information. Our framework is remarkably simple but effective: experiments demonstrate our method can generate high-quality definitions for jargon and outperform state-of-the-art models significantly, e.g., BLEU score from 8.76 to 22.66 and human-annotated score from 2.34 to 4.04.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2022-understanding">
<titleInfo>
<title>Understanding Jargon: Combining Extraction and Generation for Definition Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanyin</namePart>
<namePart type="family">Shao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">Chen-Chuan</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinjun</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen-mei</namePart>
<namePart type="family">Hwu</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>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</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>Can machines know what twin prime is? From the composition of this phrase, machines may guess twin prime is a certain kind of prime, but it is still difficult to deduce exactly what twin stands for without additional knowledge. Here, twin prime is a jargon - a specialized term used by experts in a particular field. Explaining jargon is challenging since it usually requires domain knowledge to understand. Recently, there is an increasing interest in extracting and generating definitions of words automatically. However, existing approaches, either extraction or generation, perform poorly on jargon. In this paper, we propose to combine extraction and generation for jargon definition modeling: first extract self- and correlative definitional information of target jargon from the Web and then generate the final definitions by incorporating the extracted definitional information. Our framework is remarkably simple but effective: experiments demonstrate our method can generate high-quality definitions for jargon and outperform state-of-the-art models significantly, e.g., BLEU score from 8.76 to 22.66 and human-annotated score from 2.34 to 4.04.</abstract>
<identifier type="citekey">huang-etal-2022-understanding</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.266</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.266</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>3994</start>
<end>4004</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Understanding Jargon: Combining Extraction and Generation for Definition Modeling
%A Huang, Jie
%A Shao, Hanyin
%A Chang, Kevin Chen-Chuan
%A Xiong, Jinjun
%A Hwu, Wen-mei
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F huang-etal-2022-understanding
%X Can machines know what twin prime is? From the composition of this phrase, machines may guess twin prime is a certain kind of prime, but it is still difficult to deduce exactly what twin stands for without additional knowledge. Here, twin prime is a jargon - a specialized term used by experts in a particular field. Explaining jargon is challenging since it usually requires domain knowledge to understand. Recently, there is an increasing interest in extracting and generating definitions of words automatically. However, existing approaches, either extraction or generation, perform poorly on jargon. In this paper, we propose to combine extraction and generation for jargon definition modeling: first extract self- and correlative definitional information of target jargon from the Web and then generate the final definitions by incorporating the extracted definitional information. Our framework is remarkably simple but effective: experiments demonstrate our method can generate high-quality definitions for jargon and outperform state-of-the-art models significantly, e.g., BLEU score from 8.76 to 22.66 and human-annotated score from 2.34 to 4.04.
%R 10.18653/v1/2022.emnlp-main.266
%U https://aclanthology.org/2022.emnlp-main.266
%U https://doi.org/10.18653/v1/2022.emnlp-main.266
%P 3994-4004
Markdown (Informal)
[Understanding Jargon: Combining Extraction and Generation for Definition Modeling](https://aclanthology.org/2022.emnlp-main.266) (Huang et al., EMNLP 2022)
ACL