no-3

Sentence representation using LSTM for finding question

Authors:
Linh Dinh Khanh, Huy Tran Quang
Pages:
100
View:
137
Position:
2/2
Download:
84
Learning sentence representation with the full semantics of a document is a challenge in natural language processing problems because if the semantic representation vector of the sentence is suitable, it will increase the performance of finding similar question problems. In this paper, we propose implementing a series of LSTM models with different ways of extracting sentence representations and applying them to question retrieval to exploit the hidden semantics of sentences. These methods give sentence representation from hidden layers of the LSTM model. The results show that the technique using a combination of both Max Pooling and Mean Pooling gives the highest results on the 2017 SemEval dataset for the problem of finding similarity questions.
Relate
Facial emotion recognition using deep learning technology
Hoa Nguyen Thi Thu, Ngo Huu-Huy, Tuyen Giap Manh, Duong Nong Van, Oanh Nguyen Thi Kieu
Volume 53, Issue 3A, 09/2024
Isolation and structure determine of some compounds from the methanol extract of Enhalus acoroides collected in Vietnam
HO THUY XUAN, Tran Thang Dinh, Tran Hieu Trung, Doan Phuong Lan, Duc Giang Le
Volume 53, Issue 3A, 09/2024
Overview of artificial intelligence applications in developing digital learning resources
Huế Lương Thị Minh, Vinh Nguyen The, Son Nguyen Kim, Viet Nguyen Van, Phuong Do Thi, Huong Duong Thuy
Volume 53, Issue 3A, 09/2024
Composition of fish species in the Ngan Pho River basin, Huong Son district, Ha Tinh province
Ho Anh Tuan, Hien Dinh Thi Thu, Quang Hoang Xuan
Volume 53, Issue 3A, 09/2024

Vinh University journal of science

Tạp chí khoa học Trường Đại học Vinh

ISSN: 1859 - 2228

Governing body: Vinh University

  • Address: 182 Le Duan - Vinh City - Nghe An province
  • Phone: (+84) 238.3855.452 - Fax: (+84) 238.3855.269
  • Email: vinhuni@vinhuni.edu.vn
  • Website: https://vinhuni.edu.vn

 

License: 163/GP-BTTTT issued by the Minister of Information and Communications on May 10, 2023

Open Access License: Creative Commons CC BY NC 4.0

 

CONTACT

Editor-in-Chief: Assoc. Prof., Dr. Tran Ba Tien
Email: tientb@vinhuni.edu.vn

Deputy editor-in-chief: Dr. Phan Van Tien
Email: vantienkxd@vinhuni.edu.vn

Sub-Editor: Dr. Do Mai Trang
Email: domaitrang@vinhuni.edu.vn

Editorial assistant: Msc. Le Tuan Dung, Msc. Phan The Hoa, Msc. Pham Thi Quynh Nga, Msc. Tran Thi Thai

  • Address: 4th Floor, Executive Building, No. 182, Le Duan street, Vinh city, Nghe An province.
  • Phone: (+84) 238-385-6700 | Hotline: (+84) 97-385-6700
  • Email: editors@vujs.vn
  • Website: https://vujs.vn

img