메뉴 건너뛰기
Library Notice
Institutional Access
If you certify, you can access the articles for free.
Check out your institutions.
ex)Hankuk University, Nuri Motors
Log in Register Help KOR
Subject

Multi-Domain Response Generation Using Memory-Replay Continual Learning
Recommendations
Search
Questions

기억재현 지속학습을 활용한 다중 도메인 응답 생성

논문 기본 정보

Type
Academic journal
Author
Hyeong-Jun Park (경희대학교) Choong Seon Hong (경희대학교) Seong-Bae Park (경희대학교) Hyun-Je Song (전북대학교)
Journal
Korean Institute of Information Scientists and Engineers KIISE Transactions on Computing Practices Vol.28 No.3 KCI Accredited Journals
Published
2022.3
Pages
153 - 159 (7page)
DOI
10.5626/KTCP.2022.28.3.153

Usage

cover
📌
Topic
📖
Background
🔬
Method
🏆
Result
Multi-Domain Response Generation Using Memory-Replay Continual Learning
Ask AI
Recommendations
Search
Questions

Abstract· Keywords

Report Errors
Multi-domain response generation is the task of generating responses to utterances that cover more than one domain. As the number of domains increases, multi-domain response generation must be able to respond appropriately to newly added domains as well as previously learned domains. However, previous studies based on fine-tuning with a new domain dataset have a problem that involves an inadequate response generation to pre-learned domains or a generation of domain-independent general responses. To solve this problem, the proposed model adopts a memory-replay continual learning to evolve a single-domain response generator to a multi-domain response generator. The model first learns a specific domain and retains some training instances in this domain for the next step. Then, the model is trained again with training instances for a new domain as well as the remaining instances. Since the remaining instances should represent the previous domains, the proposed method selects representative instances using clustering specialized to response generation. Through intensive experiments, the proposed method outperforms the baselines.

Contents

요약
Abstract
1. 서론
2. 기억재현 지속학습 다중 도메인 응답 생성
3. 실험
4. 결과분석
5. 결론
References

References (13)

Add References

Recommendations

It is an article recommended by DBpia according to the article similarity. Check out the related articles!

Related Authors

Frequently Viewed Together

Recently viewed articles

Comments(0)

0

Write first comments.