NAACL 2024findings2 citations

Leveraging Summarization for Unsupervised Dialogue Topic Segmentation

Aleksei Artemiev, Daniil Parinov, Alexey Grishanov, Ivan Borisov, Alexey Vasilev, Daniil Muravetskii, Aleksey Rezvykh, Aleksei Goncharov

Abstract

Traditional approaches to dialogue segmentation perform reasonably well on synthetic or written dialogues but suffer when dealing with spoken, noisy dialogs. In addition, such methods require careful tuning of hyperparameters. We propose to leverage a novel approach that is based on dialogue summaries. Experiments on different datasets showed that the new approach outperforms popular state-of-the-art algorithms in unsupervised topic segmentation and requires less setup.

BibTeX
@inproceedings{artemiev-etal-2024-leveraging,
    title = "Leveraging Summarization for Unsupervised Dialogue Topic Segmentation",
    author = "Artemiev, Aleksei  and
      Parinov, Daniil  and
      Grishanov, Alexey  and
      Borisov, Ivan  and
      Vasilev, Alexey  and
      Muravetskii, Daniil  and
      Rezvykh, Aleksey  and
      Goncharov, Aleksei  and
      Savchenko, Andrey",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-naacl.291/",
    doi = "10.18653/v1/2024.findings-naacl.291",
    pages = "4697--4704"
}
Leveraging Summarization for Unsupervised Dialogue Topic Segmentation · NAACL 2024