Recurrent Neural Network to Deep Learn Conversation in Indonesian
| Autor: | Alan Darmasaputra Chowanda, Andry Chowanda |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Perplexity
Computer science Synonym media_common.quotation_subject 02 engineering and technology computer.software_genre Machine learning Field (computer science) Synonym (database) 0202 electrical engineering electronic engineering information engineering Conversation Local language General Environmental Science media_common business.industry Deep learning 020206 networking & telecommunications DUAL (cognitive architecture) language.human_language Indonesian Recurrent neural network language General Earth and Planetary Sciences 020201 artificial intelligence & image processing Artificial intelligence business computer Natural language processing |
| Zdroj: | ICCSCI |
| ISSN: | 1877-0509 |
| DOI: | 10.1016/j.procs.2017.10.078 |
| Popis: | Natural Language Processing (NLP) is still considered a daunting task to solve for us, researcher in this field. Specifically, there is not many research has been done in a local language like Indonesian Language. Nowdays, there are hundreds of systems that require NLP as their main functions. This could be a good opportunity for us to explore this opportunity. This paper contributes models from deep learning training in Indonesian conversation using dual encoder LSTM as well as vector representation models trained with three corpora using Skip-gram method. The results show that the models are able to make a good correlation, synonym from a particular word in the words representation of vector models. In addition, the conversation models resulted in 1.07 of perplexity in the Combined model in the 14000th steps. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|