Abstract
Conversation systems accommodate diverse users with unique personalities and distinct writing styles. Within the domain of multi-turn dialogue modeling, this work studies the impact of varied utterance lengths on the quality of subsequent responses generated by conversation models. Using GPT-3 as the base model, multiple dialogue datasets, and several metrics, we conduct a thorough exploration of this aspect of conversational models. Our analysis sheds light on the complex relationship between utterance lengths and the quality of follow-up responses generated by dialogue systems. Empirical findings suggests that, for certain types of conversations, utterance lengths can be reduced by up to 72% without any noticeable difference in the quality of follow-up responses.- Anthology ID:
- 2024.teicai-1.7
- Volume:
- Proceedings of the 1st Worskhop on Towards Ethical and Inclusive Conversational AI: Language Attitudes, Linguistic Diversity, and Language Rights (TEICAI 2024)
- Month:
- March
- Year:
- 2024
- Address:
- St Julians, Malta
- Editors:
- Nina Hosseini-Kivanani, Sviatlana Höhn, Dimitra Anastasiou, Bettina Migge, Angela Soltan, Doris Dippold, Ekaterina Kamlovskaya, Fred Philippy
- Venues:
- TEICAI | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 42–49
- Language:
- URL:
- https://aclanthology.org/2024.teicai-1.7
- DOI:
- Cite (ACL):
- Yufei Tao, Tiernan Mines, and Ameeta Agrawal. 2024. Making a Long Story Short in Conversation Modeling. In Proceedings of the 1st Worskhop on Towards Ethical and Inclusive Conversational AI: Language Attitudes, Linguistic Diversity, and Language Rights (TEICAI 2024), pages 42–49, St Julians, Malta. Association for Computational Linguistics.
- Cite (Informal):
- Making a Long Story Short in Conversation Modeling (Tao et al., TEICAI-WS 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.teicai-1.7.pdf