[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

Trainable Hard Negative Examples in Contrastive Learning for Unsupervised Abstractive Summarization

Haojie Zhuang, Wei Emma Zhang, Chang Dong, Jian Yang, Quan Sheng


Abstract
Contrastive learning has demonstrated promising results in unsupervised abstractive summarization. However, existing methods rely on manually crafted negative examples, demanding substantial human effort and domain knowledge. Moreover, these human-generated negative examples may be poor in quality and lack adaptability during model training. To address these issues, we propose a novel approach that learns trainable negative examples for contrastive learning in unsupervised abstractive summarization, which eliminates the need for manual negative example design. Our framework introduces an adversarial optimization process between a negative example network and a representation network (including the summarizer and encoders). The negative example network is trained to synthesize hard negative examples that are close to the positive examples, driving the representation network to improve the quality of the generated summaries. We evaluate our method on two benchmark datasets for unsupervised abstractive summarization and observe significant performance improvements compared to strong baseline models.
Anthology ID:
2024.findings-eacl.110
Volume:
Findings of the Association for Computational Linguistics: EACL 2024
Month:
March
Year:
2024
Address:
St. Julian’s, Malta
Editors:
Yvette Graham, Matthew Purver
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1589–1600
Language:
URL:
https://aclanthology.org/2024.findings-eacl.110
DOI:
Bibkey:
Cite (ACL):
Haojie Zhuang, Wei Emma Zhang, Chang Dong, Jian Yang, and Quan Sheng. 2024. Trainable Hard Negative Examples in Contrastive Learning for Unsupervised Abstractive Summarization. In Findings of the Association for Computational Linguistics: EACL 2024, pages 1589–1600, St. Julian’s, Malta. Association for Computational Linguistics.
Cite (Informal):
Trainable Hard Negative Examples in Contrastive Learning for Unsupervised Abstractive Summarization (Zhuang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-eacl.110.pdf