When writing programs, people have the ability to tackle a new complex t...
Computational notebooks, such as Jupyter notebooks, are interactive comp...
When writing programs, people have the ability to tackle a new complex t...
Large language models have been shown to achieve remarkable performance
...
Semantic parsers map natural language utterances into meaning representa...
Program optimization is the process of modifying software to execute mor...
When humans conceive how to perform a particular task, they do so
hierar...
While most neural generative models generate outputs in a single pass, t...
Recent years have witnessed the burgeoning of pretrained language models...
Open-domain code generation aims to generate code in a general-purpose
p...
A semantic parser maps natural language commands (NLs) from the users to...
The decompiler is one of the most common tools for examining binaries wi...
Open information extraction (IE) is the task of extracting open-domain
a...
We investigate the relationship between the frequency spectrum of image ...
We introduce the problem of learning distributed representations of edit...
We present TRANX, a transition-based neural semantic parser that maps na...
In models to generate program source code from natural language, represe...
Recent advances in Neural Machine Translation (NMT) show that adding
syn...
Semantic parsing is the task of transducing natural language (NL) uttera...
For tasks like code synthesis from natural language, code retrieval, and...
Reward augmented maximum likelihood (RAML), a simple and effective learn...
We consider the problem of parsing natural language descriptions into so...
We describe DyNet, a toolkit for implementing neural network models base...
We proposed Neural Enquirer as a neural network architecture to execute ...