@inproceedings{yang-etal-2022-telin,
title = "{TELIN}: Table Entity {LIN}ker for Extracting Leaderboards from Machine Learning Publications",
author = "Yang, Sean and
Tensmeyer, Chris and
Wigington, Curtis",
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-1.3",
pages = "20--25",
abstract = "Tracking state-of-the-art (SOTA) results in machine learning studies is challenging due to high publication volume. Existing methods for creating leaderboards in scientific documents require significant human supervision or rely on scarcely available LaTeX source files. We propose Table Entity LINker (TELIN), a framework which extracts (task, model, dataset, metric) quadruples from collections of scientific publications in PDF format. TELIN identifies scientific named entities, constructs a knowledge base, and leverages human feedback to iteratively refine automatic extractions. TELIN identifies and prioritizes uncertain and impactful entities for human review to create a cascade effect for leaderboard completion. We show that TELIN is competitive with the SOTA but requires much less human annotation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2022-telin">
<titleInfo>
<title>TELIN: Table Entity LINker for Extracting Leaderboards from Machine Learning Publications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Tensmeyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Curtis</namePart>
<namePart type="family">Wigington</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>Tracking state-of-the-art (SOTA) results in machine learning studies is challenging due to high publication volume. Existing methods for creating leaderboards in scientific documents require significant human supervision or rely on scarcely available LaTeX source files. We propose Table Entity LINker (TELIN), a framework which extracts (task, model, dataset, metric) quadruples from collections of scientific publications in PDF format. TELIN identifies scientific named entities, constructs a knowledge base, and leverages human feedback to iteratively refine automatic extractions. TELIN identifies and prioritizes uncertain and impactful entities for human review to create a cascade effect for leaderboard completion. We show that TELIN is competitive with the SOTA but requires much less human annotation.</abstract>
<identifier type="citekey">yang-etal-2022-telin</identifier>
<location>
<url>https://aclanthology.org/2022.wiesp-1.3</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>20</start>
<end>25</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TELIN: Table Entity LINker for Extracting Leaderboards from Machine Learning Publications
%A Yang, Sean
%A Tensmeyer, Chris
%A Wigington, Curtis
%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 yang-etal-2022-telin
%X Tracking state-of-the-art (SOTA) results in machine learning studies is challenging due to high publication volume. Existing methods for creating leaderboards in scientific documents require significant human supervision or rely on scarcely available LaTeX source files. We propose Table Entity LINker (TELIN), a framework which extracts (task, model, dataset, metric) quadruples from collections of scientific publications in PDF format. TELIN identifies scientific named entities, constructs a knowledge base, and leverages human feedback to iteratively refine automatic extractions. TELIN identifies and prioritizes uncertain and impactful entities for human review to create a cascade effect for leaderboard completion. We show that TELIN is competitive with the SOTA but requires much less human annotation.
%U https://aclanthology.org/2022.wiesp-1.3
%P 20-25
Markdown (Informal)
[TELIN: Table Entity LINker for Extracting Leaderboards from Machine Learning Publications](https://aclanthology.org/2022.wiesp-1.3) (Yang et al., WIESP 2022)
ACL