Improving scalability of inductive logic programming via pruning and best-effort optimisation

作者：

Highlights：

• Pruning in hypothesis generalization algorithm enables learning from larger dataset.

• Using latest optimization methods for better usage of modern solver technology.

• Adding a time budget allowing the usage of suboptimal results in XHAIL.

• Obtaining competitive results and explainable hypotheses in sentence chunking.

摘要

•Pruning in hypothesis generalization algorithm enables learning from larger dataset.•Using latest optimization methods for better usage of modern solver technology.•Adding a time budget allowing the usage of suboptimal results in XHAIL.•Obtaining competitive results and explainable hypotheses in sentence chunking.

论文关键词：Answer Set Programming,Inductive logic programming,Natural Language Processing,Chunking

论文评审过程：Received 17 March 2017, Revised 19 May 2017, Accepted 9 June 2017, Available online 16 June 2017, Version of Record 23 June 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.06.013