Title:
ニューラル臨床パラフレーズ生成のためのシステム及び方法
Document Type and Number:
Japanese Patent JP6876061
Kind Code:
B2
Abstract:
The present disclosure pertains to a paraphrase generation system. The system comprises one or more hardware processors and/or other components. The system is configured to obtain a training corpus. The training corpus comprises language and known paraphrases of the language. The system is configured to generate, based on the training corpus, a word-level attention-based model and a character-level attention-based model. The system is configured to provide one or more candidate paraphrases of a natural language input based on both the word-level and character-level attention-based models. The word-level attention-based model is a word-level bidirectional long short term memory (LSTM) network and the character-level attention-based model is a character-level bidirectional LSTM network. The word-level and character level LSTM networks are generated based on words and characters in the training corpus. In some embodiments, the LSTM networks are stacked residual LSTM networks comprising residual connections between stacked layers of a given LSTM network.
Inventors:
Al Hasan Shayef Saddid
Ryu Bo
Faril Ola Dimeji Phaset
Ryu Jin Yi
Prakash Aditya
Ryu Bo
Faril Ola Dimeji Phaset
Ryu Jin Yi
Prakash Aditya
Application Number:
JP2018537859A
Publication Date:
May 26, 2021
Filing Date:
January 23, 2017
Export Citation:
Assignee:
KONINKLIJKE PHILIPS N.V.
International Classes:
G06F40/44; G06F40/151; G06N3/04; G06N20/00
Foreign References:
| US20130103390 |
Other References:
ZHANG Xiang et.al.,Character-level Convolutional Networks for Text Classification,arXiv,2015年 9月10日,pp.1-9,arXiv:1509.01626v2[cs.LG]
ボッレーガラ ダヌシカ,「Deep Learning(深層学習)」〔第6回〕自然言語処理のための深層学習,人工知能,日本,(一社)人工知能学会,2014年 3月 1日,第29巻第2号,pp.195-201
ボッレーガラ ダヌシカ,「Deep Learning(深層学習)」〔第6回〕自然言語処理のための深層学習,人工知能,日本,(一社)人工知能学会,2014年 3月 1日,第29巻第2号,pp.195-201
Attorney, Agent or Firm:
Fueda Shusen
Takahiro Igarashi
Yoshiyuki Yagabe
Takahiro Igarashi
Yoshiyuki Yagabe