@inproceedings{august-etal-2022-generating,
title = "Generating Scientific Definitions with Controllable Complexity",
author = "August, Tal and
Reinecke, Katharina and
Smith, Noah A.",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.569",
doi = "10.18653/v1/2022.acl-long.569",
pages = "8298--8317",
abstract = "Unfamiliar terminology and complex language can present barriers to understanding science. Natural language processing stands to help address these issues by automatically defining unfamiliar terms. We introduce a new task and dataset for defining scientific terms and controlling the complexity of generated definitions as a way of adapting to a specific reader{'}s background knowledge. We test four definition generation methods for this new task, finding that a sequence-to-sequence approach is most successful. We then explore the version of the task in which definitions are generated at a target complexity level. We introduce a novel reranking approach and find in human evaluations that it offers superior fluency while also controlling complexity, compared to several controllable generation baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="august-etal-2022-generating">
<titleInfo>
<title>Generating Scientific Definitions with Controllable Complexity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">August</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Reinecke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Unfamiliar terminology and complex language can present barriers to understanding science. Natural language processing stands to help address these issues by automatically defining unfamiliar terms. We introduce a new task and dataset for defining scientific terms and controlling the complexity of generated definitions as a way of adapting to a specific reader’s background knowledge. We test four definition generation methods for this new task, finding that a sequence-to-sequence approach is most successful. We then explore the version of the task in which definitions are generated at a target complexity level. We introduce a novel reranking approach and find in human evaluations that it offers superior fluency while also controlling complexity, compared to several controllable generation baselines.</abstract>
<identifier type="citekey">august-etal-2022-generating</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.569</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.569</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>8298</start>
<end>8317</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Scientific Definitions with Controllable Complexity
%A August, Tal
%A Reinecke, Katharina
%A Smith, Noah A.
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F august-etal-2022-generating
%X Unfamiliar terminology and complex language can present barriers to understanding science. Natural language processing stands to help address these issues by automatically defining unfamiliar terms. We introduce a new task and dataset for defining scientific terms and controlling the complexity of generated definitions as a way of adapting to a specific reader’s background knowledge. We test four definition generation methods for this new task, finding that a sequence-to-sequence approach is most successful. We then explore the version of the task in which definitions are generated at a target complexity level. We introduce a novel reranking approach and find in human evaluations that it offers superior fluency while also controlling complexity, compared to several controllable generation baselines.
%R 10.18653/v1/2022.acl-long.569
%U https://aclanthology.org/2022.acl-long.569
%U https://doi.org/10.18653/v1/2022.acl-long.569
%P 8298-8317
Markdown (Informal)
[Generating Scientific Definitions with Controllable Complexity](https://aclanthology.org/2022.acl-long.569) (August et al., ACL 2022)
ACL
- Tal August, Katharina Reinecke, and Noah A. Smith. 2022. Generating Scientific Definitions with Controllable Complexity. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8298–8317, Dublin, Ireland. Association for Computational Linguistics.