# Grammatical Sequence Prediction for Real-Time Neural Semantic Parsing

arXiv: https://arxiv.org/abs/1907.11049 · HTML: https://mlsanity.com/paper/1907.11049/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2019.

## Built on by (most cited first, 1 of 1)

- [Training Naturalized Semantic Parsers with Very Little Data](https://mlsanity.com/paper/2204.14243/) (2022)

## Abstract (arXiv)

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.