ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article 심층 신경망 기반 대화 처리 기술 동향
Cited - time in scopus Download 139 time Share share facebook twitter linkedin kakaostory
Authors
권오욱, 홍택규, 황금하, 노윤형, 최승권, 김화연, 김영길, 이윤근
Issue Date
2019-08
Citation
전자통신동향분석, v.34, no.4, pp.55-64
ISSN
1225-6455
Publisher
한국전자통신연구원
Language
Korean
Type
Journal Article
DOI
https://dx.doi.org/10.22648/ETRI.2019.J.340406
Abstract
In this study, we introduce trends in neural-network-based deep learning research applied to dialogue systems. Recently, end-to-end trainable goal-oriented dialogue systems using long short-term memory, sequence-tosequence models, among others, have been studied to overcome the difficulties of domain adaptation and error recognition and recovery in traditional pipeline goal-oriented dialogue systems. In addition, some research has been conducted on applying reinforcement learning to end-to-end trainable goal-oriented dialogue systems to learn dialogue strategies that do not appear in training corpora. Recent neural network models for end-to-end trainable chit-chat systems have been improved using dialogue context as well as personal and topic information to produce a more natural human conversation. Unlike previous studies that have applied different approaches to goal-oriented dialogue systems and chit-chat systems respectively, recent studies have attempted to apply end-to-end trainable approaches based on deep neural networks in common to them. Acquiring dialogue corpora for training is now necessary. Therefore, future research will focus on easily and cheaply acquiring dialogue corpora and training with small annotated dialogue corpora and/or large raw dialogues.
KSP Keywords
Deep neural network(DNN), End to End(E2E), End-to-end trainable, Goal-oriented, Long-short term memory(LSTM), Reinforcement Learning(RL), deep learning(DL), dialogue system, domain adaptation, network-based, neural network model
This work is distributed under the term of Korea Open Government License (KOGL)
(Type 4: : Type 1 + Commercial Use Prohibition+Change Prohibition)
Type 4: