A great part of software development involves conceptualizing or communicating the underlying procedures and logic that needs to be expressed in programs. One major …
We introduce Magicoder, a series of fully open-source (code, weights, and data) Large Language Models (LLMs) for code that significantly closes the gap with top code models …
H Liu, M Shen, J Zhu, N Niu, G Li… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
To release developers from time-consuming software development, many approaches have been proposed to generate source code automatically according to software requirements …
Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about …
Deep neural networks (DNN) have been shown to be notoriously brittle to small perturbations in their input data. This problem is analogous to the over-fitting problem in test …
Developers nowadays have to contend with a growing number of APIs. While in the long- term they are very useful to developers, many modern APIs have an incredibly steep …
We describe an inductive logic programming (ILP) approach called learning from failures. In this approach, an ILP system (the learner) decomposes the learning problem into three …
B Mariano, Y Chen, Y Feng, G Durrett… - Proceedings of the ACM on …, 2022 - dl.acm.org
While many mainstream languages such as Java, Python, and C# increasingly incorporate functional APIs to simplify programming and improve parallelization/performance, there are …
We consider the problem of neural semantic parsing, which translates natural language questions into executable SQL queries. We introduce a new mechanism, execution …