CoLRP: A Contrastive Learning Abstractive Text Summarization Method with ROUGE Penalty

被引:0
作者
Tan, Caidong [1 ]
Sun, Xiao [1 ]
机构
[1] Hefei Univ Technol, Sch Comp & Informat, AnHui Prov Key Lab Affect Comp & Adv Intelligent, Hefei, Peoples R China
来源
2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN | 2023年
基金
中国国家自然科学基金;
关键词
D O I
10.1109/IJCNN54540.2023.10191344
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Contrastive learning can reduce the impact of exposure bias associated with training using maximum likelihood estimation, which aims to pull together positive samples to increase the likelihood of high-quality summaries and push away irrelevant negative samples to reduce the likelihood of low-quality summaries. In contrastive learning-based text summarization methods, a standard method for selecting positive and negative samples is randomly selected within a batch. This method can lead to sampling bias to the extent that the consistency of the representation space is compromised. Therefore, we propose a new method to penalize false negatives based on ROUGE metric scores as weights to sample from the dynamic output of the model training process. The method calculates ROUGE metric scores for penalizing false negatives in real-time and can distinguish between positive and negative samples to ensure spatial consistency and alleviate exposure bias. Experimental results on XSum, CNN/DM, and Multi-News datasets show that our approach effectively improves the performance of the latest text summarization pre-training models.
引用
收藏
页数:7
相关论文
共 30 条
[1]  
Auli Michael, 2015, ICLR
[2]  
Bahdanau D., 2016, An Actor-Critic Algorithm for Sequence Prediction
[3]  
Bengio S, 2015, ADV NEUR IN, V28
[4]  
Cao ZQ, 2018, AAAI CONF ARTIF INTE, P4784
[5]  
Chopra Sumit, 2016, Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, California, DOI DOI 10.18653/V1/N16-1012
[6]  
Fabbri Alexander R, 2019, ARXIV190601749
[7]  
Fang H, 2020, ARXIV200512766
[8]  
Gunel B., 2020, ARXIV201101403
[9]  
Hadsell R., 2006, PROC IEEE C COMP UIS, P1735
[10]   Momentum Contrast for Unsupervised Visual Representation Learning [J].
He, Kaiming ;
Fan, Haoqi ;
Wu, Yuxin ;
Xie, Saining ;
Girshick, Ross .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, :9726-9735