Autoencoder for words

This paper presents a training method that encodes each word into a different vector in semantic space and its relation to low entropy coding. Elman network is employed in the method to process word sequences from literary works. The trained codes possess reduced entropy and are used in ranking, ind...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neurocomputing (Amsterdam) Jg. 139; S. 84 - 96
Hauptverfasser: Liou, Cheng-Yuan, Cheng, Wei-Chen, Liou, Jiun-Wei, Liou, Daw-Ran
Format: Journal Article Tagungsbericht
Sprache:Englisch
Veröffentlicht: Amsterdam Elsevier B.V 02.09.2014
Elsevier
Schlagworte:
Applied sciences
Artificial intelligence
Chambers
Computer science; control theory; systems
Connectionism. Neural networks
Elman network
Entropy
Exact sciences and technology
Indexing
Mathematical analysis
Minimum entropy coding
Networks
Polysemous word
Semantic indexing
Semantics
Speech and sound recognition and synthesis. Linguistics
Training
Vectors (mathematics)
Writing style similarity
Polysemous word
Elman network
Minimum entropy coding
Writing style similarity
Semantic indexing
Semantic relation
Recurrent neural nets
Literature
Hierarchical classification
Lossless compression
Entropy codes
Neural network
Vector space
Semantics
Polysemy
Chinese
Indexing
ISSN:0925-2312, 1872-8286
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper presents a training method that encodes each word into a different vector in semantic space and its relation to low entropy coding. Elman network is employed in the method to process word sequences from literary works. The trained codes possess reduced entropy and are used in ranking, indexing, and categorizing literary works. A modification of the method to train the multi-vector for each polysemous word is also presented where each vector represents a different meaning of its word. These multiple vectors can accommodate several different meanings of their word. This method is applied to the stylish analyses of two Chinese novels, Dream of the Red Chamber and Romance of the Three Kingdoms.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2013.09.055