Knowledge triple mining via multi-task learning
作者：
Highlights：
• We propose S2 AMT to solve the problem of KTM with limited seed instances.
• Our framework obtain better performance using MTL methods.
• Our framework jointly use labeled and unlabeled instances during the training stage.
• We give a fast method to find related tasks to further improve the performance.
• Our work provides a new perspective for KTM when having limited seed instances.
摘要
•We propose S2 AMT to solve the problem of KTM with limited seed instances.•Our framework obtain better performance using MTL methods.•Our framework jointly use labeled and unlabeled instances during the training stage.•We give a fast method to find related tasks to further improve the performance.•Our work provides a new perspective for KTM when having limited seed instances.
论文关键词：Multi-task learning,Knowledge mining,Relation extraction,Knowledge graph construction
论文评审过程：Received 20 November 2017, Revised 10 July 2018, Accepted 15 September 2018, Available online 19 September 2018, Version of Record 13 October 2018.
论文官网地址：https://doi.org/10.1016/j.is.2018.09.003
