Presentation | 2018-12-15 Improved accuracy of sentence classification using recurrent neural networks Mitsuhiro Komuro, Yuji Sato, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Recently various dialogue assistant products have appeared. On one hand, many of them cannot deal with flexible dialogue enough to understand sentence nuances against user's utterance, only simple question response or response by command. In this paper, we propose a model with a recurrent neural network structure, in which the middle layer is multilayered, in order to realize a classifier that judges whether the sentence is “positive” or “negative” as a preliminary stage of understanding sentence nuance in a flexible dialogue system. Experiments are conducted using 10662 movie review datasets in English. Each hyper parameter such as the learning rate and the number of layers in the middle layer, the type and number of neurons used in the middle layer were changed and the accuracy was evaluated. For the experimental result, it can be realized that it classified with accuracy of up to 84.0%. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Recurrent neural network / Sentence category classification / Natural language processing |
Paper # | NC2018-36 |
Date of Issue | 2018-12-08 (NC) |
Conference Information | |
Committee | NC / MBE |
---|---|
Conference Date | 2018/12/15(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Nagoya Institute of Technology |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Yutaka Hirata(Chubu Univ.) / Masaki Kyoso(TCU) |
Vice Chair | Hayaru Shouno(UEC) / Taishin Nomura(Osaka Univ.) |
Secretary | Hayaru Shouno(Nagoya Univ.) / Taishin Nomura(NAIST) |
Assistant | Keiichiro Inagaki(Chubu Univ.) / Takashi Shinozaki(NICT) / Takumi Kobayashi(YNU) / Yasuyuki Suzuki(Osaka Univ.) |
Paper Information | |
Registration To | Technical Committee on Neurocomputing / Technical Committee on ME and Bio Cybernetics |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Improved accuracy of sentence classification using recurrent neural networks |
Sub Title (in English) | |
Keyword(1) | Recurrent neural network |
Keyword(2) | Sentence category classification |
Keyword(3) | Natural language processing |
1st Author's Name | Mitsuhiro Komuro |
1st Author's Affiliation | Hosei University(HU) |
2nd Author's Name | Yuji Sato |
2nd Author's Affiliation | Hosei University(HU) |
Date | 2018-12-15 |
Paper # | NC2018-36 |
Volume (vol) | vol.118 |
Number (no) | NC-367 |
Page | pp.pp.47-50(NC), |
#Pages | 4 |
Date of Issue | 2018-12-08 (NC) |