Proceedings of the 2022 3rd International Conference on Artificial Intelligence and Education (IC-ICAIE 2022)

<Previous Article In Volume
Next Article In Volume>

Knowledge-enhanced Representation based-on Contrastive Learning and Informative Entities

Authors
Pingchuang Ma1, Jianhua Miao2, *, Chunyang Ruan3
1Department of information and intelligent engineering, Shanghai Publishing and Printing College, Shanghai, 200093, China
2Group of Computer Shanghai Caoyang Vocational School, Shanghai, 200333, China
3Algorithm, Shanghai Enflame Technology Company, Shanghai, 201306, China
*Corresponding author. Email: 62163346@163.com Email: luckycat336@163.com
Corresponding Author
Jianhua Miao
Available Online 27 December 2022.
DOI
10.2991/978-94-6463-040-4_190How to use a DOI?
Keywords
sentence representation; contrastive learning; knowledge enhancement; Transformer; knowledge graph
Abstract

In the field of NLP, sentence representation model is a popular task. The emergence of pre-trained representation model based on transformer structure yields significant results for downstream tasks. Besides, since the introduction of contrastive learning based on the pre-train representation model two years ago, there has been great interest in its notable benefits. For the sake of achieving better training results for sentence vector representation, we propose to use a training framework of contrastive learning and bring about knowledge graph information to improve language representation. This method enables the model to learn more linguistic information in sentence presentation and will improve the effect of sentences in tasks like semantic matching and classification.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2022 3rd International Conference on Artificial Intelligence and Education (IC-ICAIE 2022)
Series
Atlantis Highlights in Computer Sciences
Publication Date
27 December 2022
ISBN
978-94-6463-040-4
ISSN
2589-4900
DOI
10.2991/978-94-6463-040-4_190How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Pingchuang Ma
AU  - Jianhua Miao
AU  - Chunyang Ruan
PY  - 2022
DA  - 2022/12/27
TI  - Knowledge-enhanced Representation based-on Contrastive Learning and Informative Entities
BT  - Proceedings of the 2022 3rd International Conference on Artificial Intelligence and Education (IC-ICAIE 2022)
PB  - Atlantis Press
SP  - 1280
EP  - 1286
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-040-4_190
DO  - 10.2991/978-94-6463-040-4_190
ID  - Ma2022
ER  -