Attention-based Semantic Priming for Slot-filling

Jiewen Wu, Rafael E. Banchs, Luis Fernando D’Haro, Pavitra Krishnaswamy, Nancy Chen


Abstract
The problem of sequence labelling in language understanding would benefit from approaches inspired by semantic priming phenomena. We propose that an attention-based RNN architecture can be used to simulate semantic priming for sequence labelling. Specifically, we employ pre-trained word embeddings to characterize the semantic relationship between utterances and labels. We validate the approach using varying sizes of the ATIS and MEDIA datasets, and show up to 1.4-1.9% improvement in F1 score. The developed framework can enable more explainable and generalizable spoken language understanding systems.
Anthology ID:
W18-2404
Volume:
Proceedings of the Seventh Named Entities Workshop
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venue:
NEWS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
22–26
Language:
URL:
https://aclanthology.org/W18-2404
DOI:
10.18653/v1/W18-2404
Bibkey:
Cite (ACL):
Jiewen Wu, Rafael E. Banchs, Luis Fernando D’Haro, Pavitra Krishnaswamy, and Nancy Chen. 2018. Attention-based Semantic Priming for Slot-filling. In Proceedings of the Seventh Named Entities Workshop, pages 22–26, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Attention-based Semantic Priming for Slot-filling (Wu et al., NEWS 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/W18-2404.pdf