Abstract
While sequence-to-sequence (seq2seq) models achieve state-of-the-art performance in many natural language processing tasks, they can be too slow for real-time applications. One performance bottleneck is predicting the most likely next token over a large vocabulary; methods to circumvent this bottleneck are a current research topic. We focus specifically on using seq2seq models for semantic parsing, where we observe that grammars often exist which specify valid formal representations of utterance semantics. By developing a generic approach for restricting the predictions of a seq2seq model to grammatically permissible continuations, we arrive at a widely applicable technique for speeding up semantic parsing. The technique leads to a 74% speed-up on an in-house dataset with a large vocabulary, compared to the same neural model without grammatical restrictions- Anthology ID:
- W19-3902
- Volume:
- Proceedings of the Workshop on Deep Learning and Formal Languages: Building Bridges
- Month:
- August
- Year:
- 2019
- Address:
- Florence
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 14–23
- Language:
- URL:
- https://aclanthology.org/W19-3902
- DOI:
- 10.18653/v1/W19-3902
- Cite (ACL):
- Chunyang Xiao, Christoph Teichmann, and Konstantine Arkoudas. 2019. Grammatical Sequence Prediction for Real-Time Neural Semantic Parsing. In Proceedings of the Workshop on Deep Learning and Formal Languages: Building Bridges, pages 14–23, Florence. Association for Computational Linguistics.
- Cite (Informal):
- Grammatical Sequence Prediction for Real-Time Neural Semantic Parsing (Xiao et al., ACL 2019)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/W19-3902.pdf