Abstract
This paper describes Zoom’s submission to the Second Shared Task on Automatic Minuting at INLG 2023. We participated in Task A: generating abstractive summaries of meetings. Our final submission was a transformer model utilizing data from a similar domain and data augmentation by large language models, as well as content-based segmentation. The model produces summaries covering meeting topics and next steps and performs comparably to a large language model at a fraction of the cost. We also find that re-summarizing the summaries with the same model allows for an alternative, shorter summary.- Anthology ID:
- 2023.inlg-genchal.14
- Volume:
- Proceedings of the 16th International Natural Language Generation Conference: Generation Challenges
- Month:
- September
- Year:
- 2023
- Address:
- Prague, Czechia
- Editor:
- Simon Mille
- Venues:
- INLG | SIGDIAL
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 101–107
- Language:
- URL:
- https://aclanthology.org/2023.inlg-genchal.14
- DOI:
- Cite (ACL):
- Felix Schneider and Marco Turchi. 2023. Team Zoom @ AutoMin 2023: Utilizing Topic Segmentation And LLM Data Augmentation For Long-Form Meeting Summarization. In Proceedings of the 16th International Natural Language Generation Conference: Generation Challenges, pages 101–107, Prague, Czechia. Association for Computational Linguistics.
- Cite (Informal):
- Team Zoom @ AutoMin 2023: Utilizing Topic Segmentation And LLM Data Augmentation For Long-Form Meeting Summarization (Schneider & Turchi, INLG-SIGDIAL 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2023.inlg-genchal.14.pdf