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

Analysis on information retrieval performance and hardware requirement of tf-idf for open-domain QA
Recommendations
Search
Questions

오픈 도메인 QA를 위한 tf-idf의 정보 검색 성능 및 하드웨어 요구사항 분석

논문 기본 정보

Type
Proceeding
Author
Seongsik Park (서울대학교) Sungroh Yoon (서울대학교)
Journal
The Institute of Electronics and Information Engineers 대한전자공학회 학술대회 2020 IEIE SUMMER CONFERENCE
Published
2020.8
Pages
2,164 - 2,170 (7page)

Usage

cover
📌
Topic
📖
Background
🔬
Method
🏆
Result
Analysis on information retrieval performance and hardware requirement of tf-idf for open-domain QA
Ask AI
Recommendations
Search
Questions

Abstract· Keywords

Report Errors
Open―domain question answering (QA) is a natural language processing (NLP) task that predicts an answer to the given question with knowledge base. It is an intriguing and challenging NLP task that requires multiple parts of NLP. Generally, open―domain QA models consist of information retrieval models, which select the related information in the knowledge base, and a machine reader, which generates an answer based on the question and selected information. Thus, the information retrieval models have significant effects on performance and efficiency of the open―domain QA model. In this paper, to Investigate performance and requirements of the information retrieval model, we analysis the retrieval models in open―domain QA tasks. With various experiments, we showed the retrieval performance on the various configurations. In addition, we provides hardware requirements for the retrieval model including model size, required amount of data load, and operations.

Contents

Abstract
Ⅰ. 서론
Ⅱ. 배경 지식
Ⅲ. 정보 검색 모델 성능 분석
Ⅳ. 논의
Ⅴ. 결론 및 향후 연구 방향
참고문헌

References (0)

Add References

Recommendations

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

Related Authors

Recently viewed articles

Comments(0)

0

Write first comments.

UCI(KEPA) : I410-ECN-0101-2020-569-001133637