The impact of lexical and grammatical processing on generating code from natural language
Computation and Language
2022-03-17 v2
Abstract
Considering the seq2seq architecture of TranX for natural language to code translation, we identify four key components of importance: grammatical constraints, lexical preprocessing, input representations, and copy mechanisms. To study the impact of these components, we use a state-of-the-art architecture that relies on BERT encoder and a grammar-based decoder for which a formalization is provided. The paper highlights the importance of the lexical substitution component in the current natural language to code systems.
Keywords
Cite
@article{arxiv.2202.13972,
title = {The impact of lexical and grammatical processing on generating code from natural language},
author = {Nathanaël Beau and Benoît Crabbé},
journal= {arXiv preprint arXiv:2202.13972},
year = {2022}
}
Comments
Article accepted to the Findings of Association for Computational Linguistics 2022