ﻻ يوجد ملخص باللغة العربية
Traditional generative models are limited to predicting sequences of terminal tokens. However, ambiguities in the generation task may lead to incorrect outputs. Towards addressing this, we introduce Grammformers, transformer-based grammar-guided models that learn (without explicit supervision) to generate sketches -- sequences of tokens with holes. Through reinforcement learning, Grammformers learn to introduce holes avoiding the generation of incorrect tokens where there is ambiguity in the target task. We train Grammformers for statement-level source code completion, i.e., the generation of code snippets given an ambiguous user intent, such as a partial code context. We evaluate Grammformers on code completion for C# and Python and show that it generates 10-50% more accurate sketches compared to traditional generative models and 37-50% longer sketches compared to sketch-generating baselines trained with similar techniques.
Source code spends most of its time in a broken or incomplete state during software development. This presents a challenge to machine learning for code, since high-performing models typically rely on graph structured representations of programs deriv
We investigate the problem of learning to generate complex networks from data. Specifically, we consider whether deep belief networks, dependency networks, and members of the exponential random graph family can learn to generate networks whose comple
We train a network to generate mappings between training sets and classification policies (a classifier generator) by conditioning on the entire training set via an attentional mechanism. The network is directly optimized for test set performance on
Descriptive code comments are essential for supporting code comprehension and maintenance. We propose the task of automatically generating comments for overriding methods. We formulate a novel framework which accommodates the unique contextual and li
Sketch is an important media for human to communicate ideas, which reflects the superiority of human intelligence. Studies on sketch can be roughly summarized into recognition and generation. Existing models on image recognition failed to obtain sati