Abstract: Currently, the most dominant neural code generation modelsare often equipped with a tree-structured LSTM decoder, which outputs a sequence of actions to construct an Abstract Syntax Tree ...
I am a PhD student using CodeBLEU in my research on code generation evaluation. I noticed a discrepancy between the numbers reported in the paper and the results obtained using the official GitHub ...
Abstract: Over the past decade, the application of deep learning in code clone detection has produced remarkable results. However, the current approaches have two limitations: (a) code representation ...
Text-to-SQL is the task of converting a natural language utterance plus the corresponding database schema into a SQL program. The inputs naturally form a heterogeneous graph while the output SQL can ...
In the broad context of vulnerability detection, deep learning has achieved considerable progress but faces generalization challenges in multilingual environments . We introduce a novel approach named ...
The vlookup formula is a common business tool used to refer to data in one spreadsheet and retrieve data that matches what we are looking for. The vlookup formula is a function that searches for a ...
I'd like to open up the discussion of what our various options are for preserving so called "Concrete Syntax" elements in the parse tree format. A simplified definition of "concrete syntax" is any ...
On January 27, 2015, the United States Patent and Trademark Office (USPTO) issued a set of examples for analyzing claims under the abstract idea exception to subject matter patent eligibility. The ...