arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1911.04873cs.AIcs.CLcs.LG
收藏

神经网络能学习符号重写吗?

Can Neural Networks Learn Symbolic Rewriting?

Czech Technical University(捷克技术大学);University of Warsaw(华沙大学);University of Innsbruck(因斯布鲁克大学)

Bartosz Piotrowski, Josef Urban, Chad E. Brown, Cezary Kaliszyk

摘要:

这项工作调查,如果目前的神经架构是足够的学习符号重写。两种数据集提出了这项研究-一个基于自动化的证明,另一个是一个综合的多项式项集。利用现有的神经机器翻译模型进行了实验,并对其结果进行了讨论。提出了扩展这条研究路线的想法,并激发了其相关性。

英文摘要:

This work investigates if the current neural architectures are adequate for learning symbolic rewriting. Two kinds of data sets are proposed for this research -- one based on automated proofs and the other being a synthetic set of polynomial terms. The experiments with use of the current neural machine translation models are performed and its results are discussed. Ideas for extending this line of research are proposed, and its relevance is motivated.

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。

↑