2020 · 12 citations · 46 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningNatural Language ProcessingGraph-based LearningLanguage ModelingNatural Language GenerationNatural Language UnderstandingText GenerationAutomated Text GenerationCross-domain GeneralizationError DiagnosisGraph Representation LearningGraph-to-text GenerationLanguage Understanding
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.
46
The Stanford CoreNLP Natural Language Processing Toolkit
Christopher D. Manning, Mihai Surdeanu, John Bauer et al. · 2014 · 7.2K citations · Full text
Revised report on the algorithmic language ALGOL 60
John Backus, Friedrich L. Bauer, J. Green et al. · Communications of the ACM · 1963 · 909 citations · Full text
Xiaodong Gu, Hongyu Zhang, Dongmei Zhang et al. · 2016 · 497 citations