Back to Search
Start Over
Feedback recurrent neural network-based embedded vector and its application in topic model
- Source :
- EURASIP Journal on Embedded Systems. 2017(1)
- Publisher :
- Springer Nature
-
Abstract
- While mining topics in a document collection, in order to capture the relationships between words and further improve the effectiveness of discovered topics, this paper proposed a feedback recurrent neural network-based topic model. We represented each word as a one-hot vector and embedded each document into a low-dimensional vector space. During the process of document embedding, we applied the long short-term memory method to capture the backward relationships between words and proposed a feedback recurrent neural network to capture the forward relationships between words. In the topic model, we used the original and muted document pairs as positive samples and the original and random document pairs as negative samples to train the model. The experiments show that the proposed model consumes not only lower running time and memory but also has better effectiveness during topic analysis.
- Subjects :
- Topic model
General Computer Science
Computer science
business.industry
Process (computing)
02 engineering and technology
Machine learning
computer.software_genre
Data aggregator
Recurrent neural network
Control and Systems Engineering
020204 information systems
0202 electrical engineering, electronic engineering, information engineering
Embedding
020201 artificial intelligence & image processing
Artificial intelligence
business
Wireless sensor network
computer
Word (computer architecture)
Vector space
Computer Science(all)
Subjects
Details
- Language :
- English
- ISSN :
- 16873963
- Volume :
- 2017
- Issue :
- 1
- Database :
- OpenAIRE
- Journal :
- EURASIP Journal on Embedded Systems
- Accession number :
- edsair.doi.dedup.....1377b70e1da383c9b3feadce6d41037d
- Full Text :
- https://doi.org/10.1186/s13639-016-0038-6