Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPT
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929494102638592 |
|---|---|
| author | Lee, Jihyun Lee, Gary Geunbae |
| author_facet | Lee, Jihyun Lee, Gary Geunbae |
| contents | Traditional dialogue state tracking approaches heavily rely on extensive training data and handcrafted features, limiting their scalability and adaptability to new domains. In this paper, we propose a novel method that leverages inference and in-context learning with ChatGPT for domain transfer in dialogue state tracking, without any parameter updates. By guiding ChatGPT's chain of thought, we enable it to retrieve relevant examples and generalize knowledge to accurately infer dialogue states, solely through inference. Experimental results on the MultiWOZ dataset demonstrate competitive performance and promising generalization across domains. Our parameter-free approach offers a scalable and adaptable solution, opening new research directions in domain transfer learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_06243 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPT Lee, Jihyun Lee, Gary Geunbae Computation and Language Traditional dialogue state tracking approaches heavily rely on extensive training data and handcrafted features, limiting their scalability and adaptability to new domains. In this paper, we propose a novel method that leverages inference and in-context learning with ChatGPT for domain transfer in dialogue state tracking, without any parameter updates. By guiding ChatGPT's chain of thought, we enable it to retrieve relevant examples and generalize knowledge to accurately infer dialogue states, solely through inference. Experimental results on the MultiWOZ dataset demonstrate competitive performance and promising generalization across domains. Our parameter-free approach offers a scalable and adaptable solution, opening new research directions in domain transfer learning. |
| title | Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPT |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.06243 |