Abstractive summarization framework based on pre-training and contrastive learning
Abstractive summarization aims at generating sentences which can well cover the key information of the document. In this dissertation, we verify the effectiveness of a generation-evaluation model trained with contrastive learning, which generates a set of candidate summaries first and then evaluates...
Saved in:
Main Author: | Yi, Chenqi |
---|---|
Other Authors: | Lihui Chen |
Format: | Thesis-Master by Coursework |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/165534 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Multi-document summarization of dissertation abstracts using a variable-based framework
by: Ou, Shiyan, et al.
Published: (2010) -
A decoupled learning framework for contrastive learning
by: Xu, Yicheng
Published: (2022) -
Pre-training model based on the transfer learning in natural language processing
by: Tang, Jiayi
Published: (2019) -
Machine learning for image and video summarization
by: Liu, Liuziyi
Published: (2020) -
Explore contrastive learning on graph representation learning
by: Liu, Qiuyu
Published: (2022)