一句话：提出 NLU 驱动的自然语言编程框架 HISyn，无需训练样本即可媲美用数百样例训练的数据驱动方法。
自然语言编程旨在根据自然语言输入自动合成代码，近年受到广泛关注。然而现有方案多为数据驱动，需要大量带标注的训练样例。本文提出一种受人类学习编程方式启发的 NLU 驱动新思路，以自然语言理解为核心，并借助一种新颖的基于图的映射算法，从而摆脱对大量标注样例的依赖。由此构建的自然语言编程框架 HISyn 在完全不使用训练样例的情况下，其合成精度可与在数百个训练样例上训练的数据驱动方法相媲美。此外，HISyn 在可解释性、错误诊断支持以及跨领域可扩展性方面也展现出优势。
Natural Language (NL) programming automatically synthesizes code based on inputs expressed in natural language. It has recently received lots of growing interest. Recent solutions however all require many labeled training examples for their data-driven nature. This paper proposes an NLU-driven approach, a new approach inspired by how humans learn programming. It centers around Natural Language Understanding and draws on a novel graph-based mapping algorithm, foregoing the need of large numbers of labeled examples. The resulting NL programming framework, HISyn, using no training examples, gives synthesis accuracy comparable to those by data-driven methods trained on hundreds of training numbers. HISyn meanwhile demonstrates advantages in interpretability, error diagnosis support, and cross-domain extensibility.
DOI 原文 ·
@inproceedings{paperbot5865,
title = {HISyn: human learning-inspired natural language programming},
author = {Zifan Nan and Hui Guan and Xipeng Shen},
booktitle = {FSE},
year = {2020},
doi = {10.1145/3368089.3409673}
}