Abstract
We advance the state-of-the-art in unsupervised abstractive dialogue summarization by utilizing multi-sentence compression graphs. Starting from well-founded assumptions about word graphs, we present simple but reliable path-reranking and topic segmentation schemes. Robustness of our method is demonstrated on datasets across multiple domains, including meetings, interviews, movie scripts, and day-to-day conversations. We also identify possible avenues to augment our heuristic-based system with deep learning. We open-source our code, to provide a strong, reproducible baseline for future research into unsupervised dialogue summarization.- Anthology ID:
- 2022.wit-1.1
- Volume:
- Proceedings of the 2nd Workshop on Deriving Insights from User-Generated Text
- Month:
- May
- Year:
- 2022
- Address:
- (Hybrid) Dublin, Ireland, and Virtual
- Venue:
- WIT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1–9
- Language:
- URL:
- https://aclanthology.org/2022.wit-1.1
- DOI:
- 10.18653/v1/2022.wit-1.1
- Cite (ACL):
- Seongmin Park and Jihwa Lee. 2022. Unsupervised Abstractive Dialogue Summarization with Word Graphs and POV Conversion. In Proceedings of the 2nd Workshop on Deriving Insights from User-Generated Text, pages 1–9, (Hybrid) Dublin, Ireland, and Virtual. Association for Computational Linguistics.
- Cite (Informal):
- Unsupervised Abstractive Dialogue Summarization with Word Graphs and POV Conversion (Park & Lee, WIT 2022)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2022.wit-1.1.pdf
- Code
- seongminp/graph-dialogue-summary
- Data
- SAMSum Corpus