A semantics-aware approach for multilingual natural language inference.

This paper introduces a semantics-aware approach to natural language inference which allows neural network models to perform better on natural language inference benchmarks. We propose to incorporate explicit lexical and concept-level semantics from knowledge bases to improve inference accuracy. We...

Descripción completa

Detalles Bibliográficos

Publicado en:	Language Resources & Evaluation Vol. 57; no. 2; pp. 611 - 640
Autores principales:	Le-Hong, Phuong, Cambria, Erik
Formato:	Artículo
Publicado:	Springer Nature Jun2023
Materias:	Convolutional neural networks Natural languages Transformer models Inference (Logic) Artificial neural networks Recurrent neural networks
Acceso en línea:	Ver este registro en EBSCOhost