@inproceedings{silva-etal-2026-benchmarking,
title = "Benchmarking {P}ortuguese Open Information Extraction",
author = "Silva, Gabriel and
Rodrigues, M{\'a}rio and
Teixeira, Ant{\'o}nio and
Amorim, Marlene",
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-1.610/",
doi = "10.63317/2wuxjj5bo7ax",
pages = "7692--7700",
abstract = "Open Information Extraction (OIE) has seen significant advancements for English, but progress in Portuguese has been hindered by a lack of resources such as Datasets and standardized evaluation benchmarks. This work addresses this critical gap by establishing the a systematic and reproducible benchmark for Portuguese OIE systems. We conduct a comprehensive evaluation of eight systems, spanning a decade of research and encompassing both rule-based and neural architectures. The performance of these systems is measured against three distinct Portuguese corpora (WIKI200, CETEN200, and Gamalho) using the established CaRB methodology. Our results reveal that no single system excels across all three datasets. Rule-based models perform strongly on general text (WIKI200, CETEN200) but falter on specialized corpora (Gamalho), while neural systems demonstrate more consistent but not superior performance. With overall F1 scores averaging around 40{\%}, our findings confirm that Portuguese OIE remains a largely unsolved task. This benchmark provides a baseline for future research and highlights the need for a high-quality, manually annotated gold-standard dataset to drive meaningful progress in the field. The evaluation benchmark/framework is made publicly available at \url{https://github.com/gabrielrsilva11/PT-OIE-Benchmark}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="silva-etal-2026-benchmarking">
<titleInfo>
<title>Benchmarking Portuguese Open Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mário</namePart>
<namePart type="family">Rodrigues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">António</namePart>
<namePart type="family">Teixeira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marlene</namePart>
<namePart type="family">Amorim</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>Open Information Extraction (OIE) has seen significant advancements for English, but progress in Portuguese has been hindered by a lack of resources such as Datasets and standardized evaluation benchmarks. This work addresses this critical gap by establishing the a systematic and reproducible benchmark for Portuguese OIE systems. We conduct a comprehensive evaluation of eight systems, spanning a decade of research and encompassing both rule-based and neural architectures. The performance of these systems is measured against three distinct Portuguese corpora (WIKI200, CETEN200, and Gamalho) using the established CaRB methodology. Our results reveal that no single system excels across all three datasets. Rule-based models perform strongly on general text (WIKI200, CETEN200) but falter on specialized corpora (Gamalho), while neural systems demonstrate more consistent but not superior performance. With overall F1 scores averaging around 40%, our findings confirm that Portuguese OIE remains a largely unsolved task. This benchmark provides a baseline for future research and highlights the need for a high-quality, manually annotated gold-standard dataset to drive meaningful progress in the field. The evaluation benchmark/framework is made publicly available at https://github.com/gabrielrsilva11/PT-OIE-Benchmark.</abstract>
<identifier type="citekey">silva-etal-2026-benchmarking</identifier>
<identifier type="doi">10.63317/2wuxjj5bo7ax</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.610/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7692</start>
<end>7700</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Portuguese Open Information Extraction
%A Silva, Gabriel
%A Rodrigues, Mário
%A Teixeira, António
%A Amorim, Marlene
%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 silva-etal-2026-benchmarking
%X Open Information Extraction (OIE) has seen significant advancements for English, but progress in Portuguese has been hindered by a lack of resources such as Datasets and standardized evaluation benchmarks. This work addresses this critical gap by establishing the a systematic and reproducible benchmark for Portuguese OIE systems. We conduct a comprehensive evaluation of eight systems, spanning a decade of research and encompassing both rule-based and neural architectures. The performance of these systems is measured against three distinct Portuguese corpora (WIKI200, CETEN200, and Gamalho) using the established CaRB methodology. Our results reveal that no single system excels across all three datasets. Rule-based models perform strongly on general text (WIKI200, CETEN200) but falter on specialized corpora (Gamalho), while neural systems demonstrate more consistent but not superior performance. With overall F1 scores averaging around 40%, our findings confirm that Portuguese OIE remains a largely unsolved task. This benchmark provides a baseline for future research and highlights the need for a high-quality, manually annotated gold-standard dataset to drive meaningful progress in the field. The evaluation benchmark/framework is made publicly available at https://github.com/gabrielrsilva11/PT-OIE-Benchmark.
%R 10.63317/2wuxjj5bo7ax
%U https://aclanthology.org/2026.lrec-1.610/
%U https://doi.org/10.63317/2wuxjj5bo7ax
%P 7692-7700
Markdown (Informal)
[Benchmarking Portuguese Open Information Extraction](https://aclanthology.org/2026.lrec-1.610/) (Silva et al., LREC 2026)
ACL
- Gabriel Silva, Mário Rodrigues, António Teixeira, and Marlene Amorim. 2026. Benchmarking Portuguese Open Information Extraction. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 7692–7700, Palma de Mallorca, Spain. ELRA Language Resource Association.