Using BiLSTM in Dependency Parsing for Vietnamese



Título del documento: Using BiLSTM in Dependency Parsing for Vietnamese
Revista: Computación y sistemas
Base de datos:
Número de sistema: 000560352
ISSN: 1405-5546
Autores: 1
2
2
2
Instituciones: 1Dalat University, Lamdong. Vietnam
2VNU University of Science, Hanoi. Vietnam
Año:
Periodo: Jul-Sep
Volumen: 22
Número: 3
Paginación: 853-862
País: México
Idioma: Inglés
Tipo de documento: Artículo
Resumen en inglés Recently, deep learning methods have achieved good results in dependency parsing for many natural languages. In this paper, we investigate the use of bidirectional long short-term memory network models for both transition-based and graph-based dependency parsing for the Vietnamese language. We also report our contribution in building a Vietnamese dependency treebank whose tagset conforms to the Universal Dependency schema. Various experiments demonstrate the efficiency of this method, which achieves the best parsing accuracy in comparison to other existing approaches on the same corpus, with unlabeled attachment score of 84.45% or labeled attachment score of 78.56%.
Disciplinas: Ciencias de la computación
Palabras clave: Inteligencia artificial,
Aprendizaje profundo,
Modelos,
Vietnamita,
Análisis sintáctico,
Dependencia,
Procesamiento de lenguaje natural
Keyword: Deep learning,
Vietnamese,
Artificial intelligence,
Models,
Syntactic analysis,
Dependency,
Natural language processing
Texto completo: Texto completo (Ver HTML) Texto completo (Ver PDF)