Making a Long Story Short in Conversation Modeling
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916111747907584 |
|---|---|
| author | Tao, Yufei Mines, Tiernan Agrawal, Ameeta |
| author_facet | Tao, Yufei Mines, Tiernan Agrawal, Ameeta |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_00143 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Making a Long Story Short in Conversation Modeling Tao, Yufei Mines, Tiernan Agrawal, Ameeta Computation and Language Human-Computer Interaction 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. |
| title | Making a Long Story Short in Conversation Modeling |
| topic | Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2402.00143 |