QUESTION ANSWERING SYSTEM BASED ON PRE-TRAINING MODEL AND RETRIEVAL RERANKING FOR INDUSTRY 4.0

Ta Fu Chen; Yi Xing Lin; Ming Hsiang Su; Po Kai Chen; Tzu Chiang Tai; Jia Ching Wang

doi:10.1109/APSIPAASC58517.2023.10317470

QUESTION ANSWERING SYSTEM BASED ON PRE-TRAINING MODEL AND RETRIEVAL RERANKING FOR INDUSTRY 4.0

Ta Fu Chen, Yi Xing Lin, Ming Hsiang Su, Po Kai Chen, Tzu Chiang Tai, Jia Ching Wang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

By providing enhanced knowledge retrieval capabilities, real-time decision support, and efficient information exchange, question answering (QA) systems play a crucial role in driving productivity, efficiency, and innovation in Industry 4.0. Today's most reliable knowledge-based QA systems require a large knowledge base, which tends to consume more reasoning time. In order to improve the inference speed and response accuracy of the system, this paper adds a Reranker between the Retriever and Reader of the traditional two-stage mechanism. This study uses pretrained Roberta to perform system retrieval and improve data processing and training methods. Experiments on Chinese Wikipedia show that the proposed system significantly reduces the system response time and improves the accuracy and scope of the response.

Original language	English
Title of host publication	2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2178-2181
Number of pages	4
ISBN (Electronic)	9798350300673
DOIs	https://doi.org/10.1109/APSIPAASC58517.2023.10317470
State	Published - 2023
Event	2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023 - Taipei, Taiwan Duration: 31 Oct 2023 → 3 Nov 2023

Publication series

Name	2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023

Conference

Conference	2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
Country/Territory	Taiwan
City	Taipei
Period	31/10/23 → 3/11/23

Keywords

Pre-training model
QA system
Reranking

Access to Document

10.1109/APSIPAASC58517.2023.10317470

Cite this

Chen, T. F., Lin, Y. X., Su, M. H., Chen, P. K., Tai, T. C., & Wang, J. C. (2023). QUESTION ANSWERING SYSTEM BASED ON PRE-TRAINING MODEL AND RETRIEVAL RERANKING FOR INDUSTRY 4.0. In 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023 (pp. 2178-2181). (2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APSIPAASC58517.2023.10317470

Chen, Ta Fu ; Lin, Yi Xing ; Su, Ming Hsiang et al. / QUESTION ANSWERING SYSTEM BASED ON PRE-TRAINING MODEL AND RETRIEVAL RERANKING FOR INDUSTRY 4.0. 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 2178-2181 (2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023).

@inproceedings{aa96e9a503144860928a55b70fa4db5d,

title = "QUESTION ANSWERING SYSTEM BASED ON PRE-TRAINING MODEL AND RETRIEVAL RERANKING FOR INDUSTRY 4.0",

abstract = "By providing enhanced knowledge retrieval capabilities, real-time decision support, and efficient information exchange, question answering (QA) systems play a crucial role in driving productivity, efficiency, and innovation in Industry 4.0. Today's most reliable knowledge-based QA systems require a large knowledge base, which tends to consume more reasoning time. In order to improve the inference speed and response accuracy of the system, this paper adds a Reranker between the Retriever and Reader of the traditional two-stage mechanism. This study uses pretrained Roberta to perform system retrieval and improve data processing and training methods. Experiments on Chinese Wikipedia show that the proposed system significantly reduces the system response time and improves the accuracy and scope of the response.",

keywords = "Pre-training model, QA system, Reranking",

author = "Chen, {Ta Fu} and Lin, {Yi Xing} and Su, {Ming Hsiang} and Chen, {Po Kai} and Tai, {Tzu Chiang} and Wang, {Jia Ching}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023 ; Conference date: 31-10-2023 Through 03-11-2023",

year = "2023",

doi = "10.1109/APSIPAASC58517.2023.10317470",

language = "???core.languages.en_GB???",

series = "2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2178--2181",

booktitle = "2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023",

}

Chen, TF, Lin, YX, Su, MH, Chen, PK, Tai, TC & Wang, JC 2023, QUESTION ANSWERING SYSTEM BASED ON PRE-TRAINING MODEL AND RETRIEVAL RERANKING FOR INDUSTRY 4.0. in 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023. 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023, Institute of Electrical and Electronics Engineers Inc., pp. 2178-2181, 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023, Taipei, Taiwan, 31/10/23. https://doi.org/10.1109/APSIPAASC58517.2023.10317470

QUESTION ANSWERING SYSTEM BASED ON PRE-TRAINING MODEL AND RETRIEVAL RERANKING FOR INDUSTRY 4.0. / Chen, Ta Fu; Lin, Yi Xing; Su, Ming Hsiang et al.
2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 2178-2181 (2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - QUESTION ANSWERING SYSTEM BASED ON PRE-TRAINING MODEL AND RETRIEVAL RERANKING FOR INDUSTRY 4.0

AU - Chen, Ta Fu

AU - Lin, Yi Xing

AU - Su, Ming Hsiang

AU - Chen, Po Kai

AU - Tai, Tzu Chiang

AU - Wang, Jia Ching

PY - 2023

Y1 - 2023

N2 - By providing enhanced knowledge retrieval capabilities, real-time decision support, and efficient information exchange, question answering (QA) systems play a crucial role in driving productivity, efficiency, and innovation in Industry 4.0. Today's most reliable knowledge-based QA systems require a large knowledge base, which tends to consume more reasoning time. In order to improve the inference speed and response accuracy of the system, this paper adds a Reranker between the Retriever and Reader of the traditional two-stage mechanism. This study uses pretrained Roberta to perform system retrieval and improve data processing and training methods. Experiments on Chinese Wikipedia show that the proposed system significantly reduces the system response time and improves the accuracy and scope of the response.

AB - By providing enhanced knowledge retrieval capabilities, real-time decision support, and efficient information exchange, question answering (QA) systems play a crucial role in driving productivity, efficiency, and innovation in Industry 4.0. Today's most reliable knowledge-based QA systems require a large knowledge base, which tends to consume more reasoning time. In order to improve the inference speed and response accuracy of the system, this paper adds a Reranker between the Retriever and Reader of the traditional two-stage mechanism. This study uses pretrained Roberta to perform system retrieval and improve data processing and training methods. Experiments on Chinese Wikipedia show that the proposed system significantly reduces the system response time and improves the accuracy and scope of the response.

KW - Pre-training model

KW - QA system

KW - Reranking

UR - http://www.scopus.com/inward/record.url?scp=85180008183&partnerID=8YFLogxK

U2 - 10.1109/APSIPAASC58517.2023.10317470

DO - 10.1109/APSIPAASC58517.2023.10317470

M3 - 會議論文篇章

AN - SCOPUS:85180008183

T3 - 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023

SP - 2178

EP - 2181

BT - 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023

Y2 - 31 October 2023 through 3 November 2023

ER -

Chen TF, Lin YX, Su MH, Chen PK, Tai TC, Wang JC. QUESTION ANSWERING SYSTEM BASED ON PRE-TRAINING MODEL AND RETRIEVAL RERANKING FOR INDUSTRY 4.0. In 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 2178-2181. (2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023). doi: 10.1109/APSIPAASC58517.2023.10317470

QUESTION ANSWERING SYSTEM BASED ON PRE-TRAINING MODEL AND RETRIEVAL RERANKING FOR INDUSTRY 4.0

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this