@inproceedings{yoshida-etal-2024-negation-scope,
title = "Negation Scope Conversion: Towards a Unified Negation-Annotated Dataset",
author = "Yoshida, Asahi and
Kato, Yoshihide and
Matsubara, Shigeki",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1057",
pages = "12093--12099",
abstract = "Negation scope resolution is the task that identifies the part of a sentence affected by the negation cue. The three major corpora used for this task, the BioScope corpus, the SFU review corpus and the Sherlock dataset, have different annotation schemes for negation scope. Due to the different annotations, the negation scope resolution models based on pre-trained language models (PLMs) perform worse when fine-tuned on the simply combined dataset consisting of the three corpora. To address this issue, we propose a method for automatically converting the scopes of BioScope and SFU to those of Sherlock and merge them into a unified dataset. To verify the effectiveness of the proposed method, we conducted experiments using the unified dataset for fine-tuning PLM-based models. The experimental results demonstrate that the performances of the models increase when fine-tuned on the unified dataset unlike the simply combined one. In the token-level metric, the model fine-tuned on the unified dataset archived the state-of-the-art performance on the Sherlock dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yoshida-etal-2024-negation-scope">
<titleInfo>
<title>Negation Scope Conversion: Towards a Unified Negation-Annotated Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asahi</namePart>
<namePart type="family">Yoshida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshihide</namePart>
<namePart type="family">Kato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shigeki</namePart>
<namePart type="family">Matsubara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Negation scope resolution is the task that identifies the part of a sentence affected by the negation cue. The three major corpora used for this task, the BioScope corpus, the SFU review corpus and the Sherlock dataset, have different annotation schemes for negation scope. Due to the different annotations, the negation scope resolution models based on pre-trained language models (PLMs) perform worse when fine-tuned on the simply combined dataset consisting of the three corpora. To address this issue, we propose a method for automatically converting the scopes of BioScope and SFU to those of Sherlock and merge them into a unified dataset. To verify the effectiveness of the proposed method, we conducted experiments using the unified dataset for fine-tuning PLM-based models. The experimental results demonstrate that the performances of the models increase when fine-tuned on the unified dataset unlike the simply combined one. In the token-level metric, the model fine-tuned on the unified dataset archived the state-of-the-art performance on the Sherlock dataset.</abstract>
<identifier type="citekey">yoshida-etal-2024-negation-scope</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1057</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12093</start>
<end>12099</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Negation Scope Conversion: Towards a Unified Negation-Annotated Dataset
%A Yoshida, Asahi
%A Kato, Yoshihide
%A Matsubara, Shigeki
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F yoshida-etal-2024-negation-scope
%X Negation scope resolution is the task that identifies the part of a sentence affected by the negation cue. The three major corpora used for this task, the BioScope corpus, the SFU review corpus and the Sherlock dataset, have different annotation schemes for negation scope. Due to the different annotations, the negation scope resolution models based on pre-trained language models (PLMs) perform worse when fine-tuned on the simply combined dataset consisting of the three corpora. To address this issue, we propose a method for automatically converting the scopes of BioScope and SFU to those of Sherlock and merge them into a unified dataset. To verify the effectiveness of the proposed method, we conducted experiments using the unified dataset for fine-tuning PLM-based models. The experimental results demonstrate that the performances of the models increase when fine-tuned on the unified dataset unlike the simply combined one. In the token-level metric, the model fine-tuned on the unified dataset archived the state-of-the-art performance on the Sherlock dataset.
%U https://aclanthology.org/2024.lrec-main.1057
%P 12093-12099
Markdown (Informal)
[Negation Scope Conversion: Towards a Unified Negation-Annotated Dataset](https://aclanthology.org/2024.lrec-main.1057) (Yoshida et al., LREC-COLING 2024)
ACL