Two-Phase Open-Domain Question Answering System

被引：0

作者：

Prasannan, Vysakh ^{[1
]}

Shemshian, Shahin ^{[1
]}

Gurkan, Arinc ^{[1
]}

Saheer, Lakshmi Babu ^{[1
]}

Oghaz, Mahdi Maktabdar ^{[1
]}

机构：

[1] Anglia Ruskin Univ, Cambridge CB1 IPT, England

来源：

ARTIFICIAL INTELLIGENCE XXXIX, AI 2022 | 2022年 / 13652卷

关键词：

Natural language processing; NLP; K-Means; Information retrieval; TF-IDF; Encoder-Decoder; Question answering system;

D O I：

10.1007/978-3-031-21441-7_30

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Text-based Internet content is increasing at a very rapid rate day by day. As a result, even the best search engines are struggling to retrieve the exact expected results of users' queries. On many occasions, the users' expected result is embedded and scattered in a number of different documents and conventional search engines are unable to pinpoint it. To address this shortcoming, this study proposes a two-phased question answering system that utilizes a K-means clustering algorithm alongside the T5 deep encoder-decoder model to formulate a concise short answer to users' queries. The proposed system has been trained using the Kaggle QA and SQuAD datasets and achieved the maximum F1-score of 0.564 and a minimum loss of 8.56.

引用

页码：353 / 358

页数：6

共 50 条

[31] CREPE: Open-Domain Question Answering with False Presuppositions
Yu, Xinyan Velocity
Min, Sewon
Zettlemoyer, Luke
Hajishirzi, Hannaneh
PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2023): LONG PAPERS, VOL 1, 2023, : 10457 - 10480
[32] Open-Domain Non-factoid Question Answering
Khvalchik, Maria
Kulkarni, Anagha
TEXT, SPEECH, AND DIALOGUE, TSD 2017, 2017, 10415 : 290 - 298
[33] Hybrid Hierarchical Retrieval for Open-Domain Question Answering
Arivazhagan, Manoj Ghuhan
Li, Lan
Qi, Peng
Chen, Xinchi
Wang, William Yang
Huang, Zhiheng
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2023), 2023, : 10680 - 10689
[34] Visual Explanation for Open-Domain Question Answering With BERT
Shao, Zekai
Sun, Shuran
Zhao, Yuheng
Wang, Siyuan
Wei, Zhongyu
Gui, Tao
Turkay, Cagatay
Chen, Siming
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2024, 30 (07) : 3779 - 3797
[35] Learning Transferable Features for Open-Domain Question Answering
Zuin, Gianlucca
Chaimowicz, Luiz
Veloso, Adriano
2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2018,
[36] Open-Domain Question Answering with Pre-Constructed Question Spaces
Xiao, Jinfeng
Wang, Lidan
Dernoncourt, Franck
Bui, Trung
Sun, Tong
Han, Jiawei
2021 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL-HLT 2021), 2021, : 61 - 67
[37] Open-Domain Question Answering Goes Conversational via Question Rewriting
Anantha, Raviteja
Vakulenko, Svitlana
Tu, Zhucheng
Longpre, Shayne
Pulman, Stephen
Chappidi, Srinivas
2021 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL-HLT 2021), 2021, : 520 - 534
[38] Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering
Yang, Sohee
Seo, Minjoon
2021 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL-HLT 2021), 2021, : 5856 - 5865
[39] RobustQA: Benchmarking the Robustness of Domain Adaptation for Open-Domain Question Answering
Han, Rujun
Qi, Peng
Zhang, Yuhao
Liu, Lan
Burger, Juliette
Wang, William Yang
Huang, Zhiheng
Xiang, Bing
Roth, Dan
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL 2023, 2023, : 4294 - 4311
[40] Learning to Transform, Combine, and Reason in Open-Domain Question Answering
Dehghani, Mostafa
Azarbonyad, Hosein
Kamps, Jaap
de Rijke, Maarten
PROCEEDINGS OF THE TWELFTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING (WSDM'19), 2019, : 681 - 689

← 1 2 3 4 5 →