Joint Slot Filling and Intent Detection via Capsule Neural Networks

Chenwei Zhang, Yaliang Li, Nan Du, Wei Fan, Philip Yu


Abstract
Being able to recognize words as slots and detect the intent of an utterance has been a keen issue in natural language understanding. The existing works either treat slot filling and intent detection separately in a pipeline manner, or adopt joint models which sequentially label slots while summarizing the utterance-level intent without explicitly preserving the hierarchical relationship among words, slots, and intents. To exploit the semantic hierarchy for effective modeling, we propose a capsule-based neural network model which accomplishes slot filling and intent detection via a dynamic routing-by-agreement schema. A re-routing schema is proposed to further synergize the slot filling performance using the inferred intent representation. Experiments on two real-world datasets show the effectiveness of our model when compared with other alternative model architectures, as well as existing natural language understanding services.
Anthology ID:
P19-1519
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5259–5267
Language:
URL:
https://aclanthology.org/P19-1519
DOI:
10.18653/v1/P19-1519
Bibkey:
Cite (ACL):
Chenwei Zhang, Yaliang Li, Nan Du, Wei Fan, and Philip Yu. 2019. Joint Slot Filling and Intent Detection via Capsule Neural Networks. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5259–5267, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Joint Slot Filling and Intent Detection via Capsule Neural Networks (Zhang et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1519.pdf
Code
 czhang99/Capsule-NLU +  additional community code
Data
ATISSNIPS