@inproceedings{hou-etal-2021-tdmsci,
title = "{TDMS}ci: A Specialized Corpus for Scientific Literature Entity Tagging of Tasks Datasets and Metrics",
author = "Hou, Yufang and
Jochim, Charles and
Gleize, Martin and
Bonin, Francesca and
Ganguly, Debasis",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.59",
doi = "10.18653/v1/2021.eacl-main.59",
pages = "707--714",
abstract = "Tasks, Datasets and Evaluation Metrics are important concepts for understanding experimental scientific papers. However, previous work on information extraction for scientific literature mainly focuses on the abstracts only, and does not treat datasets as a separate type of entity (Zadeh and Schumann, 2016; Luan et al., 2018). In this paper, we present a new corpus that contains domain expert annotations for Task (T), Dataset (D), Metric (M) entities 2,000 sentences extracted from NLP papers. We report experiment results on TDM extraction using a simple data augmentation strategy and apply our tagger to around 30,000 NLP papers from the ACL Anthology. The corpus is made publicly available to the community for fostering research on scientific publication summarization (Erera et al., 2019) and knowledge discovery.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hou-etal-2021-tdmsci">
<titleInfo>
<title>TDMSci: A Specialized Corpus for Scientific Literature Entity Tagging of Tasks Datasets and Metrics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yufang</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charles</namePart>
<namePart type="family">Jochim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Gleize</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">Bonin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debasis</namePart>
<namePart type="family">Ganguly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Tasks, Datasets and Evaluation Metrics are important concepts for understanding experimental scientific papers. However, previous work on information extraction for scientific literature mainly focuses on the abstracts only, and does not treat datasets as a separate type of entity (Zadeh and Schumann, 2016; Luan et al., 2018). In this paper, we present a new corpus that contains domain expert annotations for Task (T), Dataset (D), Metric (M) entities 2,000 sentences extracted from NLP papers. We report experiment results on TDM extraction using a simple data augmentation strategy and apply our tagger to around 30,000 NLP papers from the ACL Anthology. The corpus is made publicly available to the community for fostering research on scientific publication summarization (Erera et al., 2019) and knowledge discovery.</abstract>
<identifier type="citekey">hou-etal-2021-tdmsci</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.59</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.59</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>707</start>
<end>714</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TDMSci: A Specialized Corpus for Scientific Literature Entity Tagging of Tasks Datasets and Metrics
%A Hou, Yufang
%A Jochim, Charles
%A Gleize, Martin
%A Bonin, Francesca
%A Ganguly, Debasis
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F hou-etal-2021-tdmsci
%X Tasks, Datasets and Evaluation Metrics are important concepts for understanding experimental scientific papers. However, previous work on information extraction for scientific literature mainly focuses on the abstracts only, and does not treat datasets as a separate type of entity (Zadeh and Schumann, 2016; Luan et al., 2018). In this paper, we present a new corpus that contains domain expert annotations for Task (T), Dataset (D), Metric (M) entities 2,000 sentences extracted from NLP papers. We report experiment results on TDM extraction using a simple data augmentation strategy and apply our tagger to around 30,000 NLP papers from the ACL Anthology. The corpus is made publicly available to the community for fostering research on scientific publication summarization (Erera et al., 2019) and knowledge discovery.
%R 10.18653/v1/2021.eacl-main.59
%U https://aclanthology.org/2021.eacl-main.59
%U https://doi.org/10.18653/v1/2021.eacl-main.59
%P 707-714
Markdown (Informal)
[TDMSci: A Specialized Corpus for Scientific Literature Entity Tagging of Tasks Datasets and Metrics](https://aclanthology.org/2021.eacl-main.59) (Hou et al., EACL 2021)
ACL