The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
A resolução do escopo de negação é o processo de detecção da parte negada de uma frase. Ao contrário da abordagem baseada em sintaxe empregada em pesquisas anteriores, os métodos de última geração tiveram melhor desempenho sem o uso explícito de estrutura sintática. Este trabalho revisita a abordagem baseada em sintaxe e reavalia a eficácia da estrutura sintática na resolução do escopo da negação. Substituímos o analisador utilizado nos trabalhos anteriores por analisadores de última geração e modificamos as regras heurísticas baseadas em sintaxe. Os resultados experimentais demonstram que as modificações simples melhoram o desempenho do método anterior baseado em sintaxe para o mesmo nível que os métodos baseados em neurais ponta a ponta de última geração.
Asahi YOSHIDA
Nagoya University
Yoshihide KATO
Nagoya University
Shigeki MATSUBARA
Nagoya University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Asahi YOSHIDA, Yoshihide KATO, Shigeki MATSUBARA, "Re-Evaluating Syntax-Based Negation Scope Resolution" in IEICE TRANSACTIONS on Information,
vol. E107-D, no. 1, pp. 165-168, January 2024, doi: 10.1587/transinf.2023EDL8050.
Abstract: Negation scope resolution is the process of detecting the negated part of a sentence. Unlike the syntax-based approach employed in previous researches, state-of-the-art methods performed better without the explicit use of syntactic structure. This work revisits the syntax-based approach and re-evaluates the effectiveness of syntactic structure in negation scope resolution. We replace the parser utilized in the prior works with state-of-the-art parsers and modify the syntax-based heuristic rules. The experimental results demonstrate that the simple modifications enhance the performance of the prior syntax-based method to the same level as state-of-the-art end-to-end neural-based methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2023EDL8050/_p
Copiar
@ARTICLE{e107-d_1_165,
author={Asahi YOSHIDA, Yoshihide KATO, Shigeki MATSUBARA, },
journal={IEICE TRANSACTIONS on Information},
title={Re-Evaluating Syntax-Based Negation Scope Resolution},
year={2024},
volume={E107-D},
number={1},
pages={165-168},
abstract={Negation scope resolution is the process of detecting the negated part of a sentence. Unlike the syntax-based approach employed in previous researches, state-of-the-art methods performed better without the explicit use of syntactic structure. This work revisits the syntax-based approach and re-evaluates the effectiveness of syntactic structure in negation scope resolution. We replace the parser utilized in the prior works with state-of-the-art parsers and modify the syntax-based heuristic rules. The experimental results demonstrate that the simple modifications enhance the performance of the prior syntax-based method to the same level as state-of-the-art end-to-end neural-based methods.},
keywords={},
doi={10.1587/transinf.2023EDL8050},
ISSN={1745-1361},
month={January},}
Copiar
TY - JOUR
TI - Re-Evaluating Syntax-Based Negation Scope Resolution
T2 - IEICE TRANSACTIONS on Information
SP - 165
EP - 168
AU - Asahi YOSHIDA
AU - Yoshihide KATO
AU - Shigeki MATSUBARA
PY - 2024
DO - 10.1587/transinf.2023EDL8050
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E107-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2024
AB - Negation scope resolution is the process of detecting the negated part of a sentence. Unlike the syntax-based approach employed in previous researches, state-of-the-art methods performed better without the explicit use of syntactic structure. This work revisits the syntax-based approach and re-evaluates the effectiveness of syntactic structure in negation scope resolution. We replace the parser utilized in the prior works with state-of-the-art parsers and modify the syntax-based heuristic rules. The experimental results demonstrate that the simple modifications enhance the performance of the prior syntax-based method to the same level as state-of-the-art end-to-end neural-based methods.
ER -