Hexa: Self-Improving for Knowledge-Grounded Dialogue System
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909365817049088 |
|---|---|
| author | Jo, Daejin Nam, Daniel Wontae Han, Gunsoo On, Kyoung-Woon Kwon, Taehwan Rho, Seungeun Kim, Sungwoong |
| author_facet | Jo, Daejin Nam, Daniel Wontae Han, Gunsoo On, Kyoung-Woon Kwon, Taehwan Rho, Seungeun Kim, Sungwoong |
| contents | A common practice in knowledge-grounded dialogue generation is to explicitly utilize intermediate steps (e.g., web-search, memory retrieval) with modular approaches. However, data for such steps are often inaccessible compared to those of dialogue responses as they are unobservable in an ordinary dialogue. To fill in the absence of these data, we develop a self-improving method to improve the generative performances of intermediate steps without the ground truth data. In particular, we propose a novel bootstrapping scheme with a guided prompt and a modified loss function to enhance the diversity of appropriate self-generated responses. Through experiments on various benchmark datasets, we empirically demonstrate that our method successfully leverages a self-improving mechanism in generating intermediate and final responses and improves the performances on the task of knowledge-grounded dialogue generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_06404 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Hexa: Self-Improving for Knowledge-Grounded Dialogue System Jo, Daejin Nam, Daniel Wontae Han, Gunsoo On, Kyoung-Woon Kwon, Taehwan Rho, Seungeun Kim, Sungwoong Computation and Language Artificial Intelligence Machine Learning A common practice in knowledge-grounded dialogue generation is to explicitly utilize intermediate steps (e.g., web-search, memory retrieval) with modular approaches. However, data for such steps are often inaccessible compared to those of dialogue responses as they are unobservable in an ordinary dialogue. To fill in the absence of these data, we develop a self-improving method to improve the generative performances of intermediate steps without the ground truth data. In particular, we propose a novel bootstrapping scheme with a guided prompt and a modified loss function to enhance the diversity of appropriate self-generated responses. Through experiments on various benchmark datasets, we empirically demonstrate that our method successfully leverages a self-improving mechanism in generating intermediate and final responses and improves the performances on the task of knowledge-grounded dialogue generation. |
| title | Hexa: Self-Improving for Knowledge-Grounded Dialogue System |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2310.06404 |