Abstract
Abstractive dialogue summarization suffers from a lots of factual errors, which are due to scattered salient elements in the multi-speaker information interaction process. In this work, we design a heterogeneous semantic slot graph with a slot-level mask cross-attention to enhance the slot features for more correct summarization. We also propose a slot-driven beam search algorithm in the decoding process to give priority to generating salient elements in a limited length by “filling-in-the-blanks”. Besides, an adversarial contrastive learning assisting the training process is introduced to alleviate the exposure bias. Experimental performance on different types of factual errors shows the effectiveness of our methods and human evaluation further verifies the results..- Anthology ID:
- 2021.findings-emnlp.209
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2435–2446
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.209
- DOI:
- 10.18653/v1/2021.findings-emnlp.209
- Cite (ACL):
- Lulu Zhao, Weihao Zeng, Weiran Xu, and Jun Guo. 2021. Give the Truth: Incorporate Semantic Slot into Abstractive Dialogue Summarization. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2435–2446, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Give the Truth: Incorporate Semantic Slot into Abstractive Dialogue Summarization (Zhao et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/ingest-bitext-workshop/2021.findings-emnlp.209.pdf
- Data
- SAMSum