HISyn: Human Learning-Inspired Natural Language Programming
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.
Fri 13 NovDisplayed time zone: (UTC) Coordinated Universal Time change
01:30 - 02:00 | |||
01:30 2mTalk | AlloyMC: Alloy Meets Model Counting Tool Demos Jiayi Yang University of Texas at Austin, USA, Wenxi Wang University of Texas at Austin, USA, Darko Marinov University of Illinois at Urbana-Champaign, Sarfraz Khurshid University of Texas at Austin DOI | ||
01:32 2mTalk | HISyn: Human Learning-Inspired Natural Language Programming Research Papers Zifan Nan North Carolina State University, USA, Hui Guan North Carolina State University, USA, Xipeng Shen North Carolina State University, USA DOI | ||
01:35 1mTalk | Inductive Program Synthesis over Noisy Data Research Papers Shivam Handa Massachusetts Institute of Technology, USA, Martin C. Rinard Massachusetts Institute of Technology, USA DOI | ||
01:37 1mTalk | MCBAT: A Practical Tool for Model Counting Constraints on Bounded Integer Arrays Tool Demos Abtin Molavi Harvey Mudd College, USA, Mara Downing Harvey Mudd College, USA, Tommy Schneider Harvey Mudd College, USA, Lucas Bang Harvey Mudd College DOI | ||
01:39 1mTalk | SVMRanker: A General Termination Analysis Framework of Loop Programs via SVM Tool Demos Xie Li , Yi Li Nanyang Technological University, Singapore, Yong Li Institute of Software, Chinese Academy of Sciences, Xuechao Sun Institute of Software at Chinese Academy of Sciences, China, Andrea Turrini State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Lijun Zhang Institute of Software, Chinese Academy of Sciences DOI | ||
01:41 19mTalk | Conversations on SAT and Synthesis Paper Presentations Abtin Molavi Harvey Mudd College, USA, Jiayi Yang University of Texas at Austin, USA, Lucas Bang Harvey Mudd College, Xie Li , Zifan Nan North Carolina State University, USA, Shivam Handa Massachusetts Institute of Technology, USA, M: Abhik Roychoudhury National University of Singapore, Singapore | ||