Dynamic Knowledge Fusion for Multi-Domain Dialogue State Tracking
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911504504193024 |
|---|---|
| author | Su, Haoxiang Fang, Ruiyu Jiang, Liting Huang, Xiaomeng Song, Shuangyong |
| author_facet | Su, Haoxiang Fang, Ruiyu Jiang, Liting Huang, Xiaomeng Song, Shuangyong |
| contents | The performance of task-oriented dialogue models is strongly tied to how well they track dialogue states, which records and updates user information across multi-turn interactions. However, current multi-domain DST encounters two key challenges: the difficulty of effectively modeling dialogue history and the limited availability of annotated data, both of which hinder model performance. To tackle the aforementioned problems, we develop a dynamic knowledge fusion framework applicable to multi-domain DST. The model operates in two stages: first, an encoder-only network trained with contrastive learning encodes dialogue history and candidate slots, selecting relevant slots based on correlation scores; second, dynamic knowledge fusion leverages the structured information of selected slots as contextual prompts to enhance the accuracy and consistency of dialogue state tracking. This design enables more accurate integration of dialogue context and domain knowledge. Results obtained from multi-domain dialogue benchmarks indicate that our method notably improves both tracking accuracy and generalization, validating its capability in handling complex dialogue scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10367 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Dynamic Knowledge Fusion for Multi-Domain Dialogue State Tracking Su, Haoxiang Fang, Ruiyu Jiang, Liting Huang, Xiaomeng Song, Shuangyong Computation and Language Artificial Intelligence The performance of task-oriented dialogue models is strongly tied to how well they track dialogue states, which records and updates user information across multi-turn interactions. However, current multi-domain DST encounters two key challenges: the difficulty of effectively modeling dialogue history and the limited availability of annotated data, both of which hinder model performance. To tackle the aforementioned problems, we develop a dynamic knowledge fusion framework applicable to multi-domain DST. The model operates in two stages: first, an encoder-only network trained with contrastive learning encodes dialogue history and candidate slots, selecting relevant slots based on correlation scores; second, dynamic knowledge fusion leverages the structured information of selected slots as contextual prompts to enhance the accuracy and consistency of dialogue state tracking. This design enables more accurate integration of dialogue context and domain knowledge. Results obtained from multi-domain dialogue benchmarks indicate that our method notably improves both tracking accuracy and generalization, validating its capability in handling complex dialogue scenarios. |
| title | Dynamic Knowledge Fusion for Multi-Domain Dialogue State Tracking |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2603.10367 |