arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.08786cs.LGcs.CL
收藏

结构化数据的语法导向变分自编码器

Syntax-Directed Variational Autoencoder for Structured Data

Georgia Institute of Technology(佐治亚理工学院);Stony Brook University(石溪大学);Ant Financial(蚂蚁金服)

Hanjun Dai, Yingtao Tian, Bo Dai, Steven Skiena, Le Song

摘要:

深度生成模型在连续数据建模方面取得了成功。然而,它仍然具有挑战性,以捕捉表示离散结构与正式的语法和语义,例如,计算机程序和分子结构。如何生成语法和语义都正确的数据仍然是一个悬而未决的问题。受编译器语法和语义检查通过语法指导翻译(SDT)完成的理论启发,通过引入随机惰性属性,提出了一种新的语法指导变分自编码器(SD-VAE).这种方法将离线SDT检查转换为用于约束解码器的实时生成的指导。与现有的方法相比,我们的方法对输出空间进行了约束,使得输出不仅在语法上有效,而且在语义上合理。我们评估所提出的模型与应用程序在程序设计语言和分子,包括重建和程序/分子优化。结果表明,在将句法和语义约束的离散生成模型,这是显着优于当前国家的最先进的方法的有效性。

英文摘要:

Deep generative models have been enjoying success in modeling continuous data. However it remains challenging to capture the representations for discrete structures with formal grammars and semantics, e.g., computer programs and molecular structures. How to generate both syntactically and semantically correct data still remains largely an open problem. Inspired by the theory of compiler where the syntax and semantics check is done via syntax-directed translation (SDT), we propose a novel syntax-directed variational autoencoder (SD-VAE) by introducing stochastic lazy attributes. This approach converts the offline SDT check into on-the-fly generated guidance for constraining the decoder. Comparing to the state-of-the-art methods, our approach enforces constraints on the output space so that the output will be not only syntactically valid, but also semantically reasonable. We evaluate the proposed model with applications in programming language and molecules, including reconstruction and program/molecule optimization. The results demonstrate the effectiveness in incorporating syntactic and semantic constraints in discrete generative models, which is significantly better than current state-of-the-art approaches.

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。

↑