Lune

ACL Findings2022

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

Nathanaël Beau, Benoît Crabbé

Abstract

Considering the seq2seq architecture of Yin and Neubig (2018) 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • RLCoder: Reinforcement Learning for Repository-Level Code Completion cites DocPrompting: Generating Code by Retrieving the Docs
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. DocPrompting: Generating Code by Retrieving the DocsShuyan Zhou, Uri Alon, Frank F. Xu, Zhengbao Jiang et al.ICLR 2023 · 18 citations
  2. RLCoder: Reinforcement Learning for Repository-Level Code CompletionYanlin Wang, Yanli Wang, Daya Guo, Jiachi Chen et al.ICSE 2025 · 13 citations
  3. InfeRE: Step-by-Step Regex Generation via Chain of InferenceShuai Zhang, Xiaodong Gu, Yuting Chen, Beijun ShenASE 2023 · 8 citations

Builds on1

  1. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations

Related papers

  1. Lexicon Learning for Few Shot Sequence ModelingEkin Akyürek, Jacob AndreasACL 2021
  2. Reproducibility Issues for BERT-based Evaluation MetricsYanran Chen, Jonas Belouadi, Steffen EgerEMNLP 2022 · 11 citations
  3. Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text GenerationYuning Mao, Wenchang Ma, Deren Lei, Jiawei Han et al.EMNLP 2021 · 2 citations
  4. SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code RepresentationsChangan Niu, Chuanyi Li, Vincent Ng, Jidong Ge et al.ICSE 2022 · 99 citations
  5. Hard-Coded Gaussian Attention for Neural Machine TranslationWeiqiu You, Simeng Sun, Mohit IyyerACL 2020 · 55 citations
Dusk over the sea between two cliffs drawn in fine vertical lines