A BiRGAT Model for Multi-intent Spoken Language Understanding with Hierarchical Semantic Frames
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910347199250432 |
|---|---|
| author | Xu, Hongshen Cao, Ruisheng Zhu, Su Jiang, Sheng Zhang, Hanchong Chen, Lu Yu, Kai |
| author_facet | Xu, Hongshen Cao, Ruisheng Zhu, Su Jiang, Sheng Zhang, Hanchong Chen, Lu Yu, Kai |
| contents | Previous work on spoken language understanding (SLU) mainly focuses on single-intent settings, where each input utterance merely contains one user intent. This configuration significantly limits the surface form of user utterances and the capacity of output semantics. In this work, we first propose a Multi-Intent dataset which is collected from a realistic in-Vehicle dialogue System, called MIVS. The target semantic frame is organized in a 3-layer hierarchical structure to tackle the alignment and assignment problems in multi-intent cases. Accordingly, we devise a BiRGAT model to encode the hierarchy of ontology items, the backbone of which is a dual relational graph attention network. Coupled with the 3-way pointer-generator decoder, our method outperforms traditional sequence labeling and classification-based schemes by a large margin. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18258 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A BiRGAT Model for Multi-intent Spoken Language Understanding with Hierarchical Semantic Frames Xu, Hongshen Cao, Ruisheng Zhu, Su Jiang, Sheng Zhang, Hanchong Chen, Lu Yu, Kai Computation and Language Previous work on spoken language understanding (SLU) mainly focuses on single-intent settings, where each input utterance merely contains one user intent. This configuration significantly limits the surface form of user utterances and the capacity of output semantics. In this work, we first propose a Multi-Intent dataset which is collected from a realistic in-Vehicle dialogue System, called MIVS. The target semantic frame is organized in a 3-layer hierarchical structure to tackle the alignment and assignment problems in multi-intent cases. Accordingly, we devise a BiRGAT model to encode the hierarchy of ontology items, the backbone of which is a dual relational graph attention network. Coupled with the 3-way pointer-generator decoder, our method outperforms traditional sequence labeling and classification-based schemes by a large margin. |
| title | A BiRGAT Model for Multi-intent Spoken Language Understanding with Hierarchical Semantic Frames |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.18258 |