Abstract
Abstractive dialogue summarization has recently been receiving more attention. We propose a coarse-to-fine model for generating abstractive dialogue summaries, and introduce a fact-aware reinforcement learning (RL) objective that improves the fact consistency between the dialogue and the generated summary. Initially, the model generates the predicate-argument spans of the dialogue, and then generates the final summary through a fact-aware RL objective. Extensive experiments and analysis on two benchmark datasets demonstrate that our proposed method effectively improves the quality of the generated summary, especially in coherence and consistency.- Anthology ID:
- 2022.findings-emnlp.248
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2022
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3408–3413
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.248
- DOI:
- Cite (ACL):
- Ye Wang, Xiaojun Wan, and Zhiping Cai. 2022. Guiding Abstractive Dialogue Summarization with Content Planning. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3408–3413, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Guiding Abstractive Dialogue Summarization with Content Planning (Wang et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.findings-emnlp.248.pdf