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 Nov Times are displayed in time zone: (UTC) Coordinated Universal Time change
01:30 - 02:00: SAT and SynthesisPaper Presentations / Research Papers / Tool Demos at Virtual room 2 | |||
01:30 - 01:32 Talk | AlloyMC: Alloy Meets Model Counting Tool Demos Jiayi YangUniversity of Texas at Austin, USA, Wenxi WangUniversity of Texas at Austin, USA, Darko MarinovUniversity of Illinois at Urbana-Champaign, Sarfraz KhurshidUniversity of Texas at Austin DOI | ||
01:32 - 01:34 Talk | HISyn: Human Learning-Inspired Natural Language Programming Research Papers Zifan NanNorth Carolina State University, USA, Hui GuanUniversity of Massachusetts at Amherst, USA, Xipeng ShenNorth Carolina State University, USA DOI | ||
01:35 - 01:36 Talk | Inductive Program Synthesis over Noisy Data Research Papers Shivam HandaMassachusetts Institute of Technology, USA, Martin RinardMassachusetts Institute of Technology, USA DOI | ||
01:37 - 01:38 Talk | MCBAT: A Practical Tool for Model Counting Constraints on Bounded Integer Arrays Tool Demos Abtin MolaviHarvey Mudd College, USA, Mara DowningHarvey Mudd College, USA, Tommy SchneiderHarvey Mudd College, USA, Lucas BangHarvey Mudd College DOI | ||
01:39 - 01:40 Talk | SVMRanker: A General Termination Analysis Framework of Loop Programs via SVM Tool Demos Xie Li, Yi LiNanyang Technological University, Singapore, Yong LiInstitute of Software, Chinese Academy of Sciences, Xuechao SunInstitute of Software at Chinese Academy of Sciences, China, Andrea TurriniState Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Lijun ZhangInstitute of Software, Chinese Academy of Sciences DOI | ||
01:41 - 02:00 Talk | Conversations on SAT and Synthesis Paper Presentations Abtin MolaviHarvey Mudd College, USA, Jiayi YangUniversity of Texas at Austin, USA, Lucas BangHarvey Mudd College, Xie Li, Zifan NanNorth Carolina State University, USA, Shivam HandaMassachusetts Institute of Technology, USA, M: Abhik RoychoudhuryNational University of Singapore, Singapore |