Transfer Learning for Multi-Premise Entailment with Relationship Processing Module

Using the single premise entailment (SPE) model to accomplish the multi-premise entailment (MPE) task can alleviate the problem that the neural network cannot be effectively trained due to the lack of labeled multi-premise training data. Moreover, the abundant judgment methods for the relationship b...

Description complète

Détails bibliographiques

Auteurs principaux:	Pin Wu, Rukang Zhu, Zhidan Lei
Format:	Artigo
Langue:	Inglês
Publié:	MDPI AG 2021-03-01
Collection:	Future Internet
Sujets:	transfer learning multi-premise entailment natural language inference attention mechanism
Accès en ligne:	https://www.mdpi.com/1999-5903/13/3/71
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!