Continual Dialogue State Tracking via Example-Guided Question Answering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911182681538560 |
|---|---|
| author | Cho, Hyundong Madotto, Andrea Lin, Zhaojiang Chandu, Khyathi Raghavi Kottur, Satwik Xu, Jing May, Jonathan Sankar, Chinnadhurai |
| author_facet | Cho, Hyundong Madotto, Andrea Lin, Zhaojiang Chandu, Khyathi Raghavi Kottur, Satwik Xu, Jing May, Jonathan Sankar, Chinnadhurai |
| contents | Dialogue systems are frequently updated to accommodate new services, but naively updating them by continually training with data for new services in diminishing performance on previously learnt services. Motivated by the insight that dialogue state tracking (DST), a crucial component of dialogue systems that estimates the user's goal as a conversation proceeds, is a simple natural language understanding task, we propose reformulating it as a bundle of granular example-guided question answering tasks to minimize the task shift between services and thus benefit continual learning. Our approach alleviates service-specific memorization and teaches a model to contextualize the given question and example to extract the necessary information from the conversation. We find that a model with just 60M parameters can achieve a significant boost by learning to learn from in-context examples retrieved by a retriever trained to identify turns with similar dialogue state changes. Combining our method with dialogue-level memory replay, our approach attains state of the art performance on DST continual learning metrics without relying on any complex regularization or parameter expansion methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_13721 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Continual Dialogue State Tracking via Example-Guided Question Answering Cho, Hyundong Madotto, Andrea Lin, Zhaojiang Chandu, Khyathi Raghavi Kottur, Satwik Xu, Jing May, Jonathan Sankar, Chinnadhurai Computation and Language Artificial Intelligence Dialogue systems are frequently updated to accommodate new services, but naively updating them by continually training with data for new services in diminishing performance on previously learnt services. Motivated by the insight that dialogue state tracking (DST), a crucial component of dialogue systems that estimates the user's goal as a conversation proceeds, is a simple natural language understanding task, we propose reformulating it as a bundle of granular example-guided question answering tasks to minimize the task shift between services and thus benefit continual learning. Our approach alleviates service-specific memorization and teaches a model to contextualize the given question and example to extract the necessary information from the conversation. We find that a model with just 60M parameters can achieve a significant boost by learning to learn from in-context examples retrieved by a retriever trained to identify turns with similar dialogue state changes. Combining our method with dialogue-level memory replay, our approach attains state of the art performance on DST continual learning metrics without relying on any complex regularization or parameter expansion methods. |
| title | Continual Dialogue State Tracking via Example-Guided Question Answering |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2305.13721 |