Unsupervised Abstractive Dialogue Summarization with Word Graphs and POV Conversion
This work provides a strong, reproducible baseline for future research in unsupervised dialogue summarization, addressing the problem of summarizing dialogues without labeled data for various domains.
The paper tackled unsupervised abstractive dialogue summarization by using multi-sentence compression graphs, achieving state-of-the-art results across multiple domains such as meetings and interviews, with robustness demonstrated on diverse datasets.
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.