Abstract
Neural abstractive summarization systems have gained significant progress in recent years. However, abstractive summarization often produce inconsisitent statements or false facts. How to automatically generate highly abstract yet factually correct summaries? In this paper, we proposed an efficient weak-supervised adversarial data augmentation approach to form the factual consistency dataset. Based on the artificial dataset, we train an evaluation model that can not only make accurate and robust factual consistency discrimination but is also capable of making interpretable factual errors tracing by backpropagated gradient distribution on token embeddings. Experiments and analysis conduct on public annotated summarization and factual consistency datasets demonstrate our approach effective and reasonable.- Anthology ID:
- 2021.emnlp-main.337
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4102–4108
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.337
- DOI:
- 10.18653/v1/2021.emnlp-main.337
- Cite (ACL):
- Zhiyuan Zeng, Jiaze Chen, Weiran Xu, and Lei Li. 2021. Gradient-Based Adversarial Factual Consistency Evaluation for Abstractive Summarization. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4102–4108, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Gradient-Based Adversarial Factual Consistency Evaluation for Abstractive Summarization (Zeng et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2021.emnlp-main.337.pdf
- Data
- CNN/Daily Mail