Abstract
We present a new neural architecture for wide-coverage Natural Language Understanding in Spoken Dialogue Systems. We develop a hierarchical multi-task architecture, which delivers a multi-layer representation of sentence meaning (i.e., Dialogue Acts and Frame-like structures). The architecture is a hierarchy of self-attention mechanisms and BiLSTM encoders followed by CRF tagging layers. We describe a variety of experiments, showing that our approach obtains promising results on a dataset annotated with Dialogue Acts and Frame Semantics. Moreover, we demonstrate its applicability to a different, publicly available NLU dataset annotated with domain-specific intents and corresponding semantic roles, providing overall performance higher than state-of-the-art tools such as RASA, Dialogflow, LUIS, and Watson. For example, we show an average 4.45% improvement in entity tagging F-score over Rasa, Dialogflow and LUIS.- Anthology ID:
- W19-5931
- Volume:
- Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
- Month:
- September
- Year:
- 2019
- Address:
- Stockholm, Sweden
- Venue:
- SIGDIAL
- SIG:
- SIGDIAL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 254–263
- Language:
- URL:
- https://aclanthology.org/W19-5931
- DOI:
- 10.18653/v1/W19-5931
- Cite (ACL):
- Andrea Vanzo, Emanuele Bastianelli, and Oliver Lemon. 2019. Hierarchical Multi-Task Natural Language Understanding for Cross-domain Conversational AI: HERMIT NLU. In Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, pages 254–263, Stockholm, Sweden. Association for Computational Linguistics.
- Cite (Informal):
- Hierarchical Multi-Task Natural Language Understanding for Cross-domain Conversational AI: HERMIT NLU (Vanzo et al., SIGDIAL 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/W19-5931.pdf
- Data
- FrameNet