arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.04335cs.AIcs.CLcs.PL
收藏

Neural Program Search:从描述和实例中解决编程任务

Neural Program Search: Solving Programming Tasks from Description and Examples

NEAR(NEAR(公司))

Illia Polosukhin, Alexander Skidanov

摘要:

我们提出了一个神经程序搜索,一个算法来生成程序从自然语言描述和少量的输入/输出的例子。该算法结合了深度学习和程序合成领域的方法,设计了丰富的领域特定语言(DSL),并在其上定义了Seq 2 Tree模型引导的高效搜索算法。为了评估该方法的质量,我们还提供了一个半合成的描述数据集,并提供了测试示例和相应的程序。我们表明,我们的算法显着优于序列到序列模型与注意力基线。

英文摘要:

We present a Neural Program Search, an algorithm to generate programs from natural language description and a small number of input/output examples. The algorithm combines methods from Deep Learning and Program Synthesis fields by designing rich domain-specific language (DSL) and defining efficient search algorithm guided by a Seq2Tree model on it. To evaluate the quality of the approach we also present a semi-synthetic dataset of descriptions with test examples and corresponding programs. We show that our algorithm significantly outperforms a sequence-to-sequence model with attention baseline.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑