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...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Neurocomputing (Amsterdam) Ročník 139; s. 84 - 96
Hlavní autori:	Liou, Cheng-Yuan, Cheng, Wei-Chen, Liou, Jiun-Wei, Liou, Daw-Ran
Médium:	Journal Article Konferenčný príspevok..
Jazyk:	English
Vydavateľské údaje:	Amsterdam Elsevier B.V 02.09.2014 Elsevier
Predmet:	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
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Buďte prvý, kto okomentuje tento záznam!