CLLGFeb 1, 2022

Natural Language to Code Using Transformers

arXiv:2202.00367v1
AI Analysis

This addresses the problem of automating code generation for developers, but it is incremental as it builds on existing transformer methods.

The paper tackles generating code snippets from natural language descriptions using the CoNaLa dataset, achieving a BLEU score of 16.99, which beats the previous baseline.

We tackle the problem of generating code snippets from natural language descriptions using the CoNaLa dataset. We use the self-attention based transformer architecture and show that it performs better than recurrent attention-based encoder decoder. Furthermore, we develop a modified form of back translation and use cycle consistent losses to train the model in an end-to-end fashion. We achieve a BLEU score of 16.99 beating the previously reported baseline of the CoNaLa challenge.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes