Task-Oriented Dialogue with In-Context Learning
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_ | 1866917593425641472 |
|---|---|
| author | Bocklisch, Tom Werkmeister, Thomas Varshneya, Daksh Nichol, Alan |
| author_facet | Bocklisch, Tom Werkmeister, Thomas Varshneya, Daksh Nichol, Alan |
| contents | We describe a system for building task-oriented dialogue systems combining the in-context learning abilities of large language models (LLMs) with the deterministic execution of business logic. LLMs are used to translate between the surface form of the conversation and a domain-specific language (DSL) which is used to progress the business logic. We compare our approach to the intent-based NLU approach predominantly used in industry today. Our experiments show that developing chatbots with our system requires significantly less effort than established approaches, that these chatbots can successfully navigate complex dialogues which are extremely challenging for NLU-based systems, and that our system has desirable properties for scaling task-oriented dialogue systems to a large number of tasks. We make our implementation available for use and further study. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12234 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Task-Oriented Dialogue with In-Context Learning Bocklisch, Tom Werkmeister, Thomas Varshneya, Daksh Nichol, Alan Computation and Language We describe a system for building task-oriented dialogue systems combining the in-context learning abilities of large language models (LLMs) with the deterministic execution of business logic. LLMs are used to translate between the surface form of the conversation and a domain-specific language (DSL) which is used to progress the business logic. We compare our approach to the intent-based NLU approach predominantly used in industry today. Our experiments show that developing chatbots with our system requires significantly less effort than established approaches, that these chatbots can successfully navigate complex dialogues which are extremely challenging for NLU-based systems, and that our system has desirable properties for scaling task-oriented dialogue systems to a large number of tasks. We make our implementation available for use and further study. |
| title | Task-Oriented Dialogue with In-Context Learning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.12234 |