@inproceedings{balachandran-etal-2018-learning,
title = "Learning to Define Terms in the Software Domain",
author = "Balachandran, Vidhisha and
Rajagopal, Dheeraj and
Kanjirathinkal, Rose Catherine and
Cohen, William",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the 2018 {EMNLP} Workshop W-{NUT}: The 4th Workshop on Noisy User-generated Text",
month = nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6122",
doi = "10.18653/v1/W18-6122",
pages = "164--172",
abstract = "One way to test a person{'}s knowledge of a domain is to ask them to define domain-specific terms. Here, we investigate the task of automatically generating definitions of technical terms by reading text from the technical domain. Specifically, we learn definitions of software entities from a large corpus built from the user forum Stack Overflow. To model definitions, we train a language model and incorporate additional domain-specific information like word co-occurrence, and ontological category information. Our approach improves previous baselines by 2 BLEU points for the definition generation task. Our experiments also show the additional challenges associated with the task and the short-comings of language-model based architectures for definition generation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="balachandran-etal-2018-learning">
<titleInfo>
<title>Learning to Define Terms in the Software Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vidhisha</namePart>
<namePart type="family">Balachandran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dheeraj</namePart>
<namePart type="family">Rajagopal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rose</namePart>
<namePart type="given">Catherine</namePart>
<namePart type="family">Kanjirathinkal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One way to test a person’s knowledge of a domain is to ask them to define domain-specific terms. Here, we investigate the task of automatically generating definitions of technical terms by reading text from the technical domain. Specifically, we learn definitions of software entities from a large corpus built from the user forum Stack Overflow. To model definitions, we train a language model and incorporate additional domain-specific information like word co-occurrence, and ontological category information. Our approach improves previous baselines by 2 BLEU points for the definition generation task. Our experiments also show the additional challenges associated with the task and the short-comings of language-model based architectures for definition generation.</abstract>
<identifier type="citekey">balachandran-etal-2018-learning</identifier>
<identifier type="doi">10.18653/v1/W18-6122</identifier>
<location>
<url>https://aclanthology.org/W18-6122</url>
</location>
<part>
<date>2018-11</date>
<extent unit="page">
<start>164</start>
<end>172</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Define Terms in the Software Domain
%A Balachandran, Vidhisha
%A Rajagopal, Dheeraj
%A Kanjirathinkal, Rose Catherine
%A Cohen, William
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F balachandran-etal-2018-learning
%X One way to test a person’s knowledge of a domain is to ask them to define domain-specific terms. Here, we investigate the task of automatically generating definitions of technical terms by reading text from the technical domain. Specifically, we learn definitions of software entities from a large corpus built from the user forum Stack Overflow. To model definitions, we train a language model and incorporate additional domain-specific information like word co-occurrence, and ontological category information. Our approach improves previous baselines by 2 BLEU points for the definition generation task. Our experiments also show the additional challenges associated with the task and the short-comings of language-model based architectures for definition generation.
%R 10.18653/v1/W18-6122
%U https://aclanthology.org/W18-6122
%U https://doi.org/10.18653/v1/W18-6122
%P 164-172
Markdown (Informal)
[Learning to Define Terms in the Software Domain](https://aclanthology.org/W18-6122) (Balachandran et al., WNUT 2018)
ACL
- Vidhisha Balachandran, Dheeraj Rajagopal, Rose Catherine Kanjirathinkal, and William Cohen. 2018. Learning to Define Terms in the Software Domain. In Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text, pages 164–172, Brussels, Belgium. Association for Computational Linguistics.