Abstract
Recent approaches have attempted to personalize dialogue systems by leveraging profile information into models. However, this knowledge is scarce and difficult to obtain, which makes the extraction/generation of profile information from dialogues a fundamental asset. To surpass this limitation, we introduce the Profile Generation Task (PGTask). We contribute with a new dataset for this problem, comprising profile sentences aligned with related utterances, extracted from a corpus of dialogues. Furthermore, using state-of-the-art methods, we provide a benchmark for profile generation on this novel dataset. Our experiments disclose the challenges of profile generation, and we hope that this introduces a new research direction.- Anthology ID:
- 2023.sigdial-1.17
- Volume:
- Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue
- Month:
- September
- Year:
- 2023
- Address:
- Prague, Czechia
- Editors:
- Svetlana Stoyanchev, Shafiq Joty, David Schlangen, Ondrej Dusek, Casey Kennington, Malihe Alikhani
- Venue:
- SIGDIAL
- SIG:
- SIGDIAL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 183–189
- Language:
- URL:
- https://aclanthology.org/2023.sigdial-1.17
- DOI:
- 10.18653/v1/2023.sigdial-1.17
- Cite (ACL):
- Rui Ribeiro, Joao Paulo Carvalho, and Luisa Coheur. 2023. PGTask: Introducing the Task of Profile Generation from Dialogues. In Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 183–189, Prague, Czechia. Association for Computational Linguistics.
- Cite (Informal):
- PGTask: Introducing the Task of Profile Generation from Dialogues (Ribeiro et al., SIGDIAL 2023)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2023.sigdial-1.17.pdf