Abstractive text summarization model combining a hierarchical attention mechanism and multiobjective reinforcement learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F24%3A10254656" target="_blank" >RIV/61989100:27240/24:10254656 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S0957417424002215?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0957417424002215?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.eswa.2024.123356" target="_blank" >10.1016/j.eswa.2024.123356</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Abstractive text summarization model combining a hierarchical attention mechanism and multiobjective reinforcement learning

Popis výsledku v původním jazyce

Text summarization research is significant and challenging in the domain of natural language processing. Abstractive text summarization mainly uses the encoder-decoder framework, wherein the encoder component does not have a sufficient semantic comprehension of the input text, and there are exposure biases and semantic inconsistencies between the reference and generated summaries during the training process. We propose an improved encoder-decoder model that incorporates a hierarchical attention mechanism and multiobjective reinforcement learning. The encoder introduces a multihead self-attention mechanism to allow for the acquisition of more comprehensive semantic information from multiple angles and dimensions, while the decoder introduces a pointer-generator network to solve the out-of-vocabulary problem. Multiobjective reinforcement learning methods are constructed throughout the training process to optimize the model in terms of addressing exposure bias, maintaining semantic consistency, and enhancing readability. The results of the comparative experiments demonstrate that the proposed model significantly improved in terms of the ROUGE evaluation metric, and the generated summaries were semantically similar to the reference summaries. (C) 2024 Elsevier Ltd

Název v anglickém jazyce

Abstractive text summarization model combining a hierarchical attention mechanism and multiobjective reinforcement learning

Popis výsledku anglicky

Text summarization research is significant and challenging in the domain of natural language processing. Abstractive text summarization mainly uses the encoder-decoder framework, wherein the encoder component does not have a sufficient semantic comprehension of the input text, and there are exposure biases and semantic inconsistencies between the reference and generated summaries during the training process. We propose an improved encoder-decoder model that incorporates a hierarchical attention mechanism and multiobjective reinforcement learning. The encoder introduces a multihead self-attention mechanism to allow for the acquisition of more comprehensive semantic information from multiple angles and dimensions, while the decoder introduces a pointer-generator network to solve the out-of-vocabulary problem. Multiobjective reinforcement learning methods are constructed throughout the training process to optimize the model in terms of addressing exposure bias, maintaining semantic consistency, and enhancing readability. The results of the comparative experiments demonstrate that the proposed model significantly improved in terms of the ROUGE evaluation metric, and the generated summaries were semantically similar to the reference summaries. (C) 2024 Elsevier Ltd

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Expert Systems with Applications

ISSN

0957-4174

e-ISSN

1873-6793

Svazek periodika

248

Číslo periodika v rámci svazku

AUG 15 2024

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

11

Strana od-do

—

Kód UT WoS článku

001186959800001

EID výsledku v databázi Scopus

2-s2.0-85185263358