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.

本文研究了 TranX 的 seq2seq 架构在自然语言到代码翻译过程中的关键组件，包括语法约束、词汇预处理、输入表示和复制机制，并通过使用 BERT 编码器和基于语法的解码器来研究这些组件的影响。研究表明，在当前的自然语言到代码系统中，词汇替换组件的重要性得到了强调。

词汇和语法处理对从自然语言生成代码的影响

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

We present TRANX, a transition-based neural semantic parser that maps natural
language (NL) utterances into formal meaning representations (MRs). TRANX uses
a transition system based on the abstract syntax description language for the
target MR, which gives it two major advantages: (1) it is highly accurate,
using information from the syntax of the target MR to constrain the output
space and model the information flow, and (2) it is highly generalizable, and
can easily be applied to new types of MR by just writing a new abstract syntax
description corresponding to the allowable structures in the MR. Experiments on
four different semantic parsing and code generation tasks show that our system
is generalizable, extensible, and effective, registering strong results
compared to existing neural semantic parsers.

该研究提出了一种基于转换的神经语义解析器 TRANX，它通过一个基于抽象语法描述语言的转换系统将自然语言表达转化为形式化的意义表示，从而具有高准确性和高可泛化性。实验表明，TRANX 相对于现有神经语义解析器，在处理四种不同的语义分析和代码生成任务时具有可扩展性和效率，并取得了强劲的结果。