@inproceedings{collard-etal-2022-extracting,
title = "Extracting Mathematical Concepts from Text",
author = "Collard, Jacob and
de Paiva, Valeria and
Fong, Brendan and
Subrahmanian, Eswaran",
booktitle = "Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wnut-1.2",
pages = "15--23",
abstract = "We investigate different systems for extracting mathematical entities from English texts in the mathematical field of category theory as a first step for constructing a mathematical knowledge graph. We consider four different term extractors and compare their results. This small experiment showcases some of the issues with the construction and evaluation of terms extracted from noisy domain text. We also make available two open corpora in research mathematics, in particular in category theory: a small corpus of 755 abstracts from the journal TAC (3188 sentences), and a larger corpus from the nLab community wiki (15,000 sentences)",
}

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="collard-etal-2022-extracting">
<titleInfo>
<title>Extracting Mathematical Concepts from Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Collard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valeria</namePart>
<namePart type="family">de Paiva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brendan</namePart>
<namePart type="family">Fong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eswaran</namePart>
<namePart type="family">Subrahmanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We investigate different systems for extracting mathematical entities from English texts in the mathematical field of category theory as a first step for constructing a mathematical knowledge graph. We consider four different term extractors and compare their results. This small experiment showcases some of the issues with the construction and evaluation of terms extracted from noisy domain text. We also make available two open corpora in research mathematics, in particular in category theory: a small corpus of 755 abstracts from the journal TAC (3188 sentences), and a larger corpus from the nLab community wiki (15,000 sentences)</abstract>
<identifier type="citekey">collard-etal-2022-extracting</identifier>
<location>
<url>https://aclanthology.org/2022.wnut-1.2</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>15</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Extracting Mathematical Concepts from Text
%A Collard, Jacob
%A de Paiva, Valeria
%A Fong, Brendan
%A Subrahmanian, Eswaran
%S Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F collard-etal-2022-extracting
%X We investigate different systems for extracting mathematical entities from English texts in the mathematical field of category theory as a first step for constructing a mathematical knowledge graph. We consider four different term extractors and compare their results. This small experiment showcases some of the issues with the construction and evaluation of terms extracted from noisy domain text. We also make available two open corpora in research mathematics, in particular in category theory: a small corpus of 755 abstracts from the journal TAC (3188 sentences), and a larger corpus from the nLab community wiki (15,000 sentences)
%U https://aclanthology.org/2022.wnut-1.2
%P 15-23

##### Markdown (Informal)

[Extracting Mathematical Concepts from Text](https://aclanthology.org/2022.wnut-1.2) (Collard et al., WNUT 2022)

##### ACL

- Jacob Collard, Valeria de Paiva, Brendan Fong, and Eswaran Subrahmanian. 2022. Extracting Mathematical Concepts from Text. In
*Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)*, pages 15–23, Gyeongju, Republic of Korea. Association for Computational Linguistics.