LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911827820019712 |
|---|---|
| author | Kumar, Nalin Dušek, Ondřej |
| author_facet | Kumar, Nalin Dušek, Ondřej |
| contents | Linguistic entrainment, or alignment, represents a phenomenon where linguistic patterns employed by conversational participants converge to one another. While entrainment has been shown to produce a more natural user experience, most dialogue systems do not have any provisions for it. In this work, we introduce methods for achieving dialogue entrainment in a GPT-2-based end-to-end task-oriented dialogue system through the utilization of shared vocabulary. We experiment with training instance weighting, entrainment-specific loss, and additional conditioning to generate responses that align with the user. We demonstrate that all three approaches produce significantly better entrainment than the base, non-entrainment-optimized model, as confirmed by both automated and manual evaluation metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_09390 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems Kumar, Nalin Dušek, Ondřej Computation and Language Linguistic entrainment, or alignment, represents a phenomenon where linguistic patterns employed by conversational participants converge to one another. While entrainment has been shown to produce a more natural user experience, most dialogue systems do not have any provisions for it. In this work, we introduce methods for achieving dialogue entrainment in a GPT-2-based end-to-end task-oriented dialogue system through the utilization of shared vocabulary. We experiment with training instance weighting, entrainment-specific loss, and additional conditioning to generate responses that align with the user. We demonstrate that all three approaches produce significantly better entrainment than the base, non-entrainment-optimized model, as confirmed by both automated and manual evaluation metrics. |
| title | LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2311.09390 |