TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities
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_ | 1866916434550980608 |
|---|---|
| author | Zhang, Ming Huang, Caishuang Wu, Yilong Liu, Shichun Zheng, Huiyuan Dong, Yurui Shen, Yujiong Dou, Shihan Zhao, Jun Ye, Junjie Zhang, Qi Gui, Tao Huang, Xuanjing |
| author_facet | Zhang, Ming Huang, Caishuang Wu, Yilong Liu, Shichun Zheng, Huiyuan Dong, Yurui Shen, Yujiong Dou, Shihan Zhao, Jun Ye, Junjie Zhang, Qi Gui, Tao Huang, Xuanjing |
| contents | Task-oriented dialogue (TOD) systems aim to efficiently handle task-oriented conversations, including information collection. How to utilize TOD accurately, efficiently and effectively for information collection has always been a critical and challenging task. Recent studies have demonstrated that Large Language Models (LLMs) excel in dialogue, instruction generation, and reasoning, and can significantly enhance the performance of TOD through fine-tuning. However, current datasets primarily cater to user-led systems and are limited to predefined specific scenarios and slots, thereby necessitating improvements in the proactiveness, diversity, and capabilities of TOD. In this study, we present a detailed multi-domain task-oriented data construction process for conversations, and a Chinese dialogue dataset generated based on this process, TransferTOD, which authentically simulates human-computer dialogues in 30 popular life service scenarios. Leveraging this dataset, we trained a model called TransferTOD-7B using full-parameter fine-tuning, showcasing notable abilities in slot filling and questioning. Our work has demonstrated its strong generalization capabilities in various downstream scenarios, significantly enhancing both data utilization efficiency and system performance. The data is released in https://github.com/KongLongGeFDU/TransferTOD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_21693 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities Zhang, Ming Huang, Caishuang Wu, Yilong Liu, Shichun Zheng, Huiyuan Dong, Yurui Shen, Yujiong Dou, Shihan Zhao, Jun Ye, Junjie Zhang, Qi Gui, Tao Huang, Xuanjing Artificial Intelligence Task-oriented dialogue (TOD) systems aim to efficiently handle task-oriented conversations, including information collection. How to utilize TOD accurately, efficiently and effectively for information collection has always been a critical and challenging task. Recent studies have demonstrated that Large Language Models (LLMs) excel in dialogue, instruction generation, and reasoning, and can significantly enhance the performance of TOD through fine-tuning. However, current datasets primarily cater to user-led systems and are limited to predefined specific scenarios and slots, thereby necessitating improvements in the proactiveness, diversity, and capabilities of TOD. In this study, we present a detailed multi-domain task-oriented data construction process for conversations, and a Chinese dialogue dataset generated based on this process, TransferTOD, which authentically simulates human-computer dialogues in 30 popular life service scenarios. Leveraging this dataset, we trained a model called TransferTOD-7B using full-parameter fine-tuning, showcasing notable abilities in slot filling and questioning. Our work has demonstrated its strong generalization capabilities in various downstream scenarios, significantly enhancing both data utilization efficiency and system performance. The data is released in https://github.com/KongLongGeFDU/TransferTOD. |
| title | TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2407.21693 |