Papers Program Synthesis
“Program Synthesis” 태그가 달린 논문 538편 · 필터 해제
Compositional Generalization and Decomposition in Neural Program Synthesis
When writing programs, people have the ability to tackle a new complex task by decomposing it into smaller and more familiar subtasks. While it is difficult to measure whether neural program synthesis methods have simila…
Program SynthesisEfficient Pragmatic Program Synthesis with Informative Specifications
Providing examples is one of the most common way for end-users to interact with program synthesizers. However, program synthesis systems assume that examples consistent with the program are chosen at random, and do not e…
Program SynthesisCodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
Program synthesis strives to generate a computer program as a solution to a given problem specification, expressed with input-output examples or natural language descriptions. The prevalence of large language models adva…
Code GenerationHumanEvalLanguage ModelingLanguage Modelling+2CrossBeam: Learning to Search in Bottom-Up Program Synthesis
Many approaches to program synthesis perform a search within an enormous space of programs to find one that satisfies a given specification. Prior works have used neural models to guide combinatorial search algorithms, b…
Program SynthesisStructured PredictionLess is More: Summary of Long Instructions is Better for Program Synthesis
Despite the success of large pre-trained language models (LMs) such as Codex, they show below-par performance on the larger and more complicated programming related questions. We show that LMs benefit from the summarized…
Program SynthesisIterative Genetic Improvement: Scaling Stochastic Program Synthesis
Program synthesis aims to {\it automatically} find programs from an underlying programming language that satisfy a given specification. While this has the potential to revolutionize computing, how to search over the vast…
Program SynthesisLearning Program Synthesis for Integer Sequences from Scratch
We present a self-learning approach for synthesizing programs from integer sequences. Our method relies on a tree search guided by a learned policy. Our system is tested on the On-Line Encyclopedia of Integer Sequences. …
Program SynthesisSelf-LearningGPT-based Open-Ended Knowledge Tracing
In education applications, knowledge tracing refers to the problem of estimating students' time-varying concept/skill mastery level from their past responses to questions and predicting their future performance. One key …
Code GenerationKnowledge TracingNavigateProgram Synthesis+1Learning logic programs by discovering where not to search
The goal of inductive logic programming (ILP) is to search for a hypothesis that generalises training examples and background knowledge (BK). To improve performance, we introduce an approach that, before searching for a …
Inductive logic programmingProgram SynthesisSapientML: Synthesizing Machine Learning Pipelines by Learning from Human-Written Solutions
Automatic machine learning, or AutoML, holds the promise of truly democratizing the use of machine learning (ML), by substantially automating the work of data scientists. However, the huge combinatorial search space of c…
AutoMLBIG-bench Machine LearningProgram SynthesisExplanatory Learning: Beyond Empiricism in Neural Networks
We introduce Explanatory Learning (EL), a framework to let machines use existing knowledge buried in symbolic sequences -- e.g. explanations written in hieroglyphic -- by autonomously learning to interpret them. In EL, t…
Binary ClassificationProgram SynthesisSynthesizing explainable counterfactual policies for algorithmic recourse with program synthesis
Being able to provide counterfactual interventions - sequences of actions we would have had to take for a desirable outcome to happen - is essential to explain how to change an unfavourable decision by a black-box machin…
counterfactualEfficient ExplorationProgram SynthesisFrom Examples to Rules: Neural Guided Rule Synthesis for Information Extraction
While deep learning approaches to information extraction have had many successes, they can be difficult to augment or maintain as needs shift. Rule-based methods, on the other hand, can be more easily modified. However, …
Enumerative SearchFew-Shot LearningProgram SynthesisRelation ClassificationMWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving
Math word problem (MWP) solving faces a dilemma in number representation learning. In order to avoid the number representation issue and reduce the search space of feasible solutions, existing works striving for MWP solv…
Language ModelingLanguage ModellingMathMath Word Problem Solving+2A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level
We demonstrate that a neural network pre-trained on text and fine-tuned on code solves mathematics course problems, explains solutions, and generates new questions at a human level. We automatically synthesize programs u…
Few-Shot LearningLanguage ModellingMathMathematical Reasoning+2Differentiable Synthesis of Program Architectures
Differentiable programs have recently attracted much interest due to their interpretability, compositionality, and their efficiency to leverage differentiable training. However, synthesizing differentiable programs requi…
Program SynthesisStress Rules from Surface Forms: Experiments with Program Synthesis
Learning linguistic generalizations from only a few examples is a challenging task. Recent work has shown that program synthesis – a method to learn rules from data in the form of programs in a domain-specific language –…
Program SynthesisAutomatic Synthesis of Diverse Weak Supervision Sources for Behavior Analysis
Obtaining annotations for large training sets is expensive, especially in settings where domain knowledge is required, such as behavior analysis. Weak supervision has been studied to reduce annotation costs by using weak…
DiversityProgram SynthesisSolving Visual Analogies Using Neural Algorithmic Reasoning
We consider a class of visual analogical reasoning problems that involve discovering the sequence of transformations by which pairs of input/output images are related, so as to analogously transform future inputs. This p…
Program SynthesisVisual AnalogiesSolving Probability and Statistics Problems by Program Synthesis
We solve university level probability and statistics questions by program synthesis using OpenAI's Codex, a Transformer trained on text and fine-tuned on code. We transform course problems from MIT's 18.05 Introduction t…
FormProgram SynthesisPrompt Engineering