@inproceedings{ghosh-etal-2022-astro,
title = "Astro-m{T}5: Entity Extraction from Astrophysics Literature using m{T}5 Language Model",
author = "Ghosh, Madhusudan and
Santra, Payel and
Iqbal, Sk Asif and
Basuchowdhuri, Partha",
editor = "Ghosal, Tirthankar and
Blanco-Cuaresma, Sergi and
Accomazzi, Alberto and
Patton, Robert M. and
Grezes, Felix and
Allen, Thomas",
booktitle = "Proceedings of the first Workshop on Information Extraction from Scientific Publications",
month = nov,
year = "2022",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wiesp-1.12",
pages = "100--104",
abstract = "Scientific research requires reading and extracting relevant information from existing scientific literature in an effective way. To gain insights over a collection of such scientific documents, extraction of entities and recognizing their types is considered to be one of the important tasks. Numerous studies have been conducted in this area of research. In our study, we introduce a framework for entity recognition and identification of NASA astrophysics dataset, which was published as a part of the DEAL SharedTask. We use a pre-trained multilingual model, based on a natural language processing framework for the given sequence labeling tasks. Experiments show that our model, Astro-mT5, out-performs the existing baseline in astrophysics related information extraction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghosh-etal-2022-astro">
<titleInfo>
<title>Astro-mT5: Entity Extraction from Astrophysics Literature using mT5 Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Madhusudan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Payel</namePart>
<namePart type="family">Santra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sk</namePart>
<namePart type="given">Asif</namePart>
<namePart type="family">Iqbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Partha</namePart>
<namePart type="family">Basuchowdhuri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the first Workshop on Information Extraction from Scientific Publications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergi</namePart>
<namePart type="family">Blanco-Cuaresma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Accomazzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Patton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Grezes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Allen</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>Scientific research requires reading and extracting relevant information from existing scientific literature in an effective way. To gain insights over a collection of such scientific documents, extraction of entities and recognizing their types is considered to be one of the important tasks. Numerous studies have been conducted in this area of research. In our study, we introduce a framework for entity recognition and identification of NASA astrophysics dataset, which was published as a part of the DEAL SharedTask. We use a pre-trained multilingual model, based on a natural language processing framework for the given sequence labeling tasks. Experiments show that our model, Astro-mT5, out-performs the existing baseline in astrophysics related information extraction.</abstract>
<identifier type="citekey">ghosh-etal-2022-astro</identifier>
<location>
<url>https://aclanthology.org/2022.wiesp-1.12</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>100</start>
<end>104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Astro-mT5: Entity Extraction from Astrophysics Literature using mT5 Language Model
%A Ghosh, Madhusudan
%A Santra, Payel
%A Iqbal, Sk Asif
%A Basuchowdhuri, Partha
%Y Ghosal, Tirthankar
%Y Blanco-Cuaresma, Sergi
%Y Accomazzi, Alberto
%Y Patton, Robert M.
%Y Grezes, Felix
%Y Allen, Thomas
%S Proceedings of the first Workshop on Information Extraction from Scientific Publications
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online
%F ghosh-etal-2022-astro
%X Scientific research requires reading and extracting relevant information from existing scientific literature in an effective way. To gain insights over a collection of such scientific documents, extraction of entities and recognizing their types is considered to be one of the important tasks. Numerous studies have been conducted in this area of research. In our study, we introduce a framework for entity recognition and identification of NASA astrophysics dataset, which was published as a part of the DEAL SharedTask. We use a pre-trained multilingual model, based on a natural language processing framework for the given sequence labeling tasks. Experiments show that our model, Astro-mT5, out-performs the existing baseline in astrophysics related information extraction.
%U https://aclanthology.org/2022.wiesp-1.12
%P 100-104
Markdown (Informal)
[Astro-mT5: Entity Extraction from Astrophysics Literature using mT5 Language Model](https://aclanthology.org/2022.wiesp-1.12) (Ghosh et al., WIESP 2022)
ACL