The impact of lexical and grammatical processing on generating code from natural language [article]

Nathanaël Beau, Benoît Crabbé
2022 arXiv   pre-print
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.
arXiv:2202.13972v2 fatcat:ysttkiutl5dsvhunhgumemiwje