Lifelong Language Learning With the Most Forgotten Knowledge
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choi, Heejeong | - |
dc.contributor.author | Kang, Pilsung | - |
dc.date.accessioned | 2021-12-07T21:42:05Z | - |
dc.date.available | 2021-12-07T21:42:05Z | - |
dc.date.created | 2021-08-30 | - |
dc.date.issued | 2021 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/130179 | - |
dc.description.abstract | Lifelong language learning enables a language model to accumulate knowledge through training on a stream of text data. Recent research on lifelong language learning is based on samples of previous tasks from an episodic memory or generative model. LAMOL, a representative generative model-based lifelong language learning model, preserves the previous information with the generated pseudo-old samples, which are suboptimal. In this paper, we propose an improved version of LAMOL, MFK-LAMOL, which constructs a generative replay using a more effective method. When a new task is received, MFK-LAMOL replays sufficient previous data and retrieves important examples for training alongside the new task. Specifically, it selects the examples with the most forgotten knowledge learned from previous tasks based on the extent to which they include knowledge that has been forgotten after learning new information. We showed that the proposed method outperforms LAMOL on a stream of three different natural language processing tasks. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Lifelong Language Learning With the Most Forgotten Knowledge | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kang, Pilsung | - |
dc.identifier.doi | 10.1109/ACCESS.2021.3071787 | - |
dc.identifier.scopusid | 2-s2.0-85104201655 | - |
dc.identifier.wosid | 000641941800001 | - |
dc.identifier.bibliographicCitation | IEEE ACCESS, v.9, pp.57941 - 57948 | - |
dc.relation.isPartOf | IEEE ACCESS | - |
dc.citation.title | IEEE ACCESS | - |
dc.citation.volume | 9 | - |
dc.citation.startPage | 57941 | - |
dc.citation.endPage | 57948 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.subject.keywordAuthor | Task analysis | - |
dc.subject.keywordAuthor | Training | - |
dc.subject.keywordAuthor | Natural language processing | - |
dc.subject.keywordAuthor | Neural networks | - |
dc.subject.keywordAuthor | Data models | - |
dc.subject.keywordAuthor | Knowledge discovery | - |
dc.subject.keywordAuthor | Measurement | - |
dc.subject.keywordAuthor | Lifelong language learning | - |
dc.subject.keywordAuthor | natural language processing | - |
dc.subject.keywordAuthor | catastrophic forgetting | - |
dc.subject.keywordAuthor | a stream of text data | - |
dc.subject.keywordAuthor | generative replay | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.