Improved Chinese Sentence Semantic Similarity Calculation Method Based on Multi-Feature Fusion

In this paper, an improved long short-term memory (LSTM)-based deep neural network structure is proposed for learning variable-length Chinese sentence semantic similarities. Siamese LSTM, a sequence-insensitive deep neural network model, has a limited ability to capture the semantics of natural lang...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of advanced computational intelligence and intelligent informatics 2021-07, Vol.25 (4), p.442-449
Hauptverfasser:	Liu, Liqi, Wang, Qinglin, Li, Yuan
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Machine learning Neural networks Representations Semantics Sentences Similarity Words (language)
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!