-
Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis
The use of deep learning techniques has achieved significant progress fo...
read it
-
Neural Guided Constraint Logic Programming for Program Synthesis
Synthesizing programs using example input/outputs is a classic problem i...
read it
-
BUSTLE: Bottom-up program-Synthesis Through Learning-guided Exploration
Program synthesis is challenging largely because of the difficulty of se...
read it
-
Optimal Neural Program Synthesis from Multimodal Specifications
Multimodal program synthesis, which leverages different types of user in...
read it
-
Synthesizing Symmetric Lenses
Lenses are programs that can be run both "front to back" and "back to fr...
read it
-
Neurally-Guided Structure Inference
Most structure inference methods either rely on exhaustive search or are...
read it
-
NIL: Learning Nonlinear Interpolants
Nonlinear interpolants have been shown useful for the verification of pr...
read it
Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples
Synthesizing user-intended programs from a small number of input-output examples is a challenging problem with several important applications like spreadsheet manipulation, data wrangling and code refactoring. Existing synthesis systems either completely rely on deductive logic techniques that are extensively hand-engineered or on purely statistical models that need massive amounts of data, and in general fail to provide real-time synthesis on challenging benchmarks. In this work, we propose Neural Guided Deductive Search (NGDS), a hybrid synthesis technique that combines the best of both symbolic logic techniques and statistical models. Thus, it produces programs that satisfy the provided specifications by construction and generalize well on unseen examples, similar to data-driven systems. Our technique effectively utilizes the deductive search framework to reduce the learning problem of the neural component to a simple supervised learning setup. Further, this allows us to both train on sparingly available real-world data and still leverage powerful recurrent neural network encoders. We demonstrate the effectiveness of our method by evaluating on real-world customer scenarios by synthesizing accurate programs with up to 12x speed-up compared to state-of-the-art systems.
READ FULL TEXT
Comments
There are no comments yet.