@inproceedings{ettaleb-etal-2026-retat,
title = "{R}e{T}a{T}: A Unified Benchmark for Relation Extraction across Text and Table",
author = "Ettaleb, Mohamed and
Ehrhart, Thibault and
Aussenac-Gilles, Nathalie and
Chabot, Yoan and
Kamel, Mouna and
MORICEAU, V{\'e}ronique and
Troncy, Raphael and
Wei, Fanfu",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.104/",
doi = "10.63317/4k8jqsbkjuir",
pages = "1341--1351",
abstract = "While prior work in Information Extraction (IE) has focused on extracting information from either textual content or tables in isolation, they miss critical information that emerges only from their interplay. Indeed, tables may summarize facts sparse in the text, while text can disambiguate or elaborate on table entries. This complementarity may take the form of relations which are expressed across text and tables. In this context, we are interested in the task of extracting such relations whose expression spans the two modalities. This task is an original one, for which no reference evaluation corpora exists. Thus we created ReTaT, a corpus that can be used to train and evaluate systems for extracting such relations. This corpus is composed of (table, surrounding text) pairs extracted from Wikipedia pages and has been manually annotated with relation triples. ReTaT is organized in three datasets with distinct characteristics: domain (business, telecommunication and female celebrities), size (from 50 to 255 pairs), language (English vs French), type of relations (data vs object properties), close vs open list of relation, size of the surrounding text (paragraph vs full page). We then assessed its quality and suitability for the joint table-text relation extraction task using Large Language Models (LLMs), at a time when LLMs have demonstrated their ability to extract relations from either text or tables in isolation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ettaleb-etal-2026-retat">
<titleInfo>
<title>ReTaT: A Unified Benchmark for Relation Extraction across Text and Table</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Ettaleb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thibault</namePart>
<namePart type="family">Ehrhart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathalie</namePart>
<namePart type="family">Aussenac-Gilles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoan</namePart>
<namePart type="family">Chabot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mouna</namePart>
<namePart type="family">Kamel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Véronique</namePart>
<namePart type="family">MORICEAU</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raphael</namePart>
<namePart type="family">Troncy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fanfu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While prior work in Information Extraction (IE) has focused on extracting information from either textual content or tables in isolation, they miss critical information that emerges only from their interplay. Indeed, tables may summarize facts sparse in the text, while text can disambiguate or elaborate on table entries. This complementarity may take the form of relations which are expressed across text and tables. In this context, we are interested in the task of extracting such relations whose expression spans the two modalities. This task is an original one, for which no reference evaluation corpora exists. Thus we created ReTaT, a corpus that can be used to train and evaluate systems for extracting such relations. This corpus is composed of (table, surrounding text) pairs extracted from Wikipedia pages and has been manually annotated with relation triples. ReTaT is organized in three datasets with distinct characteristics: domain (business, telecommunication and female celebrities), size (from 50 to 255 pairs), language (English vs French), type of relations (data vs object properties), close vs open list of relation, size of the surrounding text (paragraph vs full page). We then assessed its quality and suitability for the joint table-text relation extraction task using Large Language Models (LLMs), at a time when LLMs have demonstrated their ability to extract relations from either text or tables in isolation.</abstract>
<identifier type="citekey">ettaleb-etal-2026-retat</identifier>
<identifier type="doi">10.63317/4k8jqsbkjuir</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.104/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1341</start>
<end>1351</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReTaT: A Unified Benchmark for Relation Extraction across Text and Table
%A Ettaleb, Mohamed
%A Ehrhart, Thibault
%A Aussenac-Gilles, Nathalie
%A Chabot, Yoan
%A Kamel, Mouna
%A MORICEAU, Véronique
%A Troncy, Raphael
%A Wei, Fanfu
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F ettaleb-etal-2026-retat
%X While prior work in Information Extraction (IE) has focused on extracting information from either textual content or tables in isolation, they miss critical information that emerges only from their interplay. Indeed, tables may summarize facts sparse in the text, while text can disambiguate or elaborate on table entries. This complementarity may take the form of relations which are expressed across text and tables. In this context, we are interested in the task of extracting such relations whose expression spans the two modalities. This task is an original one, for which no reference evaluation corpora exists. Thus we created ReTaT, a corpus that can be used to train and evaluate systems for extracting such relations. This corpus is composed of (table, surrounding text) pairs extracted from Wikipedia pages and has been manually annotated with relation triples. ReTaT is organized in three datasets with distinct characteristics: domain (business, telecommunication and female celebrities), size (from 50 to 255 pairs), language (English vs French), type of relations (data vs object properties), close vs open list of relation, size of the surrounding text (paragraph vs full page). We then assessed its quality and suitability for the joint table-text relation extraction task using Large Language Models (LLMs), at a time when LLMs have demonstrated their ability to extract relations from either text or tables in isolation.
%R 10.63317/4k8jqsbkjuir
%U https://aclanthology.org/2026.lrec-1.104/
%U https://doi.org/10.63317/4k8jqsbkjuir
%P 1341-1351
Markdown (Informal)
[ReTaT: A Unified Benchmark for Relation Extraction across Text and Table](https://aclanthology.org/2026.lrec-1.104/) (Ettaleb et al., LREC 2026)
ACL
- Mohamed Ettaleb, Thibault Ehrhart, Nathalie Aussenac-Gilles, Yoan Chabot, Mouna Kamel, Véronique MORICEAU, Raphael Troncy, and Fanfu Wei. 2026. ReTaT: A Unified Benchmark for Relation Extraction across Text and Table. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 1341–1351, Palma de Mallorca, Spain. ELRA Language Resource Association.