English

Unsupervised Abstractive Dialogue Summarization with Word Graphs and POV Conversion

Computation and Language 2022-05-27 v1 Artificial Intelligence

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.

Keywords

Cite

@article{arxiv.2205.13108,
  title  = {Unsupervised Abstractive Dialogue Summarization with Word Graphs and POV Conversion},
  author = {Seongmin Park and Jihwa Lee},
  journal= {arXiv preprint arXiv:2205.13108},
  year   = {2022}
}

Comments

WIT Workshop @ ACL2022

R2 v1 2026-06-24T11:29:06.111Z