@inproceedings{singh-etal-2022-relation,
title = "A Relation Extraction Dataset for Knowledge Extraction from Web Tables",
author = "Singh, Siffi and
Aji, Alham Fikri and
Singh, Gaurav and
Christodoulopoulos, Christos",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.203",
pages = "2319--2327",
abstract = "Relational web-tables are significant sources of structural information that are widely used for relation extraction and population of facts into knowledge graphs. To transform the web-table data into knowledge, we need to identify the relations that exist between column pairs. Currently, there are only a handful of publicly available datasets with relations annotated against natural web-tables. Most datasets are constructed using synthetic tables that lack valuable metadata information, or are limited in size to be considered as a challenging evaluation set. In this paper, we present REDTab, the largest natural-table relation extraction dataset. We have annotated {\textasciitilde}9K tables and {\textasciitilde}22K column pairs using crowd sourced annotators from MTurk, which has 50x larger number of column pairs than the existing human-annotated benchmark. Our test set is specially designed to be challenging as observed in our experiment results using TaBERT. We publicly release REDTab as a benchmark for the evaluation process in relation extraction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2022-relation">
<titleInfo>
<title>A Relation Extraction Dataset for Knowledge Extraction from Web Tables</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siffi</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alham</namePart>
<namePart type="given">Fikri</namePart>
<namePart type="family">Aji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaurav</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</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 29th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Relational web-tables are significant sources of structural information that are widely used for relation extraction and population of facts into knowledge graphs. To transform the web-table data into knowledge, we need to identify the relations that exist between column pairs. Currently, there are only a handful of publicly available datasets with relations annotated against natural web-tables. Most datasets are constructed using synthetic tables that lack valuable metadata information, or are limited in size to be considered as a challenging evaluation set. In this paper, we present REDTab, the largest natural-table relation extraction dataset. We have annotated ~9K tables and ~22K column pairs using crowd sourced annotators from MTurk, which has 50x larger number of column pairs than the existing human-annotated benchmark. Our test set is specially designed to be challenging as observed in our experiment results using TaBERT. We publicly release REDTab as a benchmark for the evaluation process in relation extraction.</abstract>
<identifier type="citekey">singh-etal-2022-relation</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.203</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>2319</start>
<end>2327</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Relation Extraction Dataset for Knowledge Extraction from Web Tables
%A Singh, Siffi
%A Aji, Alham Fikri
%A Singh, Gaurav
%A Christodoulopoulos, Christos
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F singh-etal-2022-relation
%X Relational web-tables are significant sources of structural information that are widely used for relation extraction and population of facts into knowledge graphs. To transform the web-table data into knowledge, we need to identify the relations that exist between column pairs. Currently, there are only a handful of publicly available datasets with relations annotated against natural web-tables. Most datasets are constructed using synthetic tables that lack valuable metadata information, or are limited in size to be considered as a challenging evaluation set. In this paper, we present REDTab, the largest natural-table relation extraction dataset. We have annotated ~9K tables and ~22K column pairs using crowd sourced annotators from MTurk, which has 50x larger number of column pairs than the existing human-annotated benchmark. Our test set is specially designed to be challenging as observed in our experiment results using TaBERT. We publicly release REDTab as a benchmark for the evaluation process in relation extraction.
%U https://aclanthology.org/2022.coling-1.203
%P 2319-2327
Markdown (Informal)
[A Relation Extraction Dataset for Knowledge Extraction from Web Tables](https://aclanthology.org/2022.coling-1.203) (Singh et al., COLING 2022)
ACL