@inproceedings{heinecke-etal-2026-creating,
title = "Creating a High Quality {A}bstract {M}eaning {R}epresentation Dataset Automatically",
author = "Heinecke, Johannes and
Asadullah, Munshi and
Herledan, Fr{\'e}d{\'e}ric and
Damnati, Geraldine",
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-1.932/",
doi = "10.63317/3qai4xpkg9v4",
pages = "11907--11915",
abstract = "As only a few gold training datasets are available today, Abstract Meaning Representation (AMR) parsers are mainly trained on AMR 3.0, the largest dataset (Knight et al., 2020) which contains 55k sentences for training. Even if great progress has been made, leading to parsers that can reach Smatch scores higher than 83{\%} on the AMR 3.0 test dataset, this is not accurate enough to be used in real world application pipelines. More data could help improve performance, but manually annotating sentences is costly. So, we have investigated an approach to automatically create synthetic data using different existing tools and models trained on AMR 3.0. This leads to better parsing performance with Smatch scores increased by 1 to 2 points (depending on the 3 gold test datasets used) with models trained on the augmented data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="heinecke-etal-2026-creating">
<titleInfo>
<title>Creating a High Quality Abstract Meaning Representation Dataset Automatically</title>
</titleInfo>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Heinecke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Munshi</namePart>
<namePart type="family">Asadullah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Herledan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geraldine</namePart>
<namePart type="family">Damnati</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>As only a few gold training datasets are available today, Abstract Meaning Representation (AMR) parsers are mainly trained on AMR 3.0, the largest dataset (Knight et al., 2020) which contains 55k sentences for training. Even if great progress has been made, leading to parsers that can reach Smatch scores higher than 83% on the AMR 3.0 test dataset, this is not accurate enough to be used in real world application pipelines. More data could help improve performance, but manually annotating sentences is costly. So, we have investigated an approach to automatically create synthetic data using different existing tools and models trained on AMR 3.0. This leads to better parsing performance with Smatch scores increased by 1 to 2 points (depending on the 3 gold test datasets used) with models trained on the augmented data.</abstract>
<identifier type="citekey">heinecke-etal-2026-creating</identifier>
<identifier type="doi">10.63317/3qai4xpkg9v4</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.932/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>11907</start>
<end>11915</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating a High Quality Abstract Meaning Representation Dataset Automatically
%A Heinecke, Johannes
%A Asadullah, Munshi
%A Herledan, Frédéric
%A Damnati, Geraldine
%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 heinecke-etal-2026-creating
%X As only a few gold training datasets are available today, Abstract Meaning Representation (AMR) parsers are mainly trained on AMR 3.0, the largest dataset (Knight et al., 2020) which contains 55k sentences for training. Even if great progress has been made, leading to parsers that can reach Smatch scores higher than 83% on the AMR 3.0 test dataset, this is not accurate enough to be used in real world application pipelines. More data could help improve performance, but manually annotating sentences is costly. So, we have investigated an approach to automatically create synthetic data using different existing tools and models trained on AMR 3.0. This leads to better parsing performance with Smatch scores increased by 1 to 2 points (depending on the 3 gold test datasets used) with models trained on the augmented data.
%R 10.63317/3qai4xpkg9v4
%U https://aclanthology.org/2026.lrec-1.932/
%U https://doi.org/10.63317/3qai4xpkg9v4
%P 11907-11915
Markdown (Informal)
[Creating a High Quality Abstract Meaning Representation Dataset Automatically](https://aclanthology.org/2026.lrec-1.932/) (Heinecke et al., LREC 2026)
ACL