Mitigating the Effect of Out-of-Vocabulary Entity Pairs in Matrix Factorization for KB Inference

被引:0
作者
Jain, Prachi [1 ]
Murty, Shikhar [1 ]
Mausam [1 ]
Chakrabarti, Soumen [2 ]
机构
[1] Indian Inst Technol Delhi, Delhi, India
[2] Indian Inst Technol, Bombay, Maharashtra, India
来源
PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE | 2018年
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper analyzes the varied performance of Matrix Factorization (MF) on the related tasks of relation extraction and knowledge-base completion, which have been unified recently into a single framework of knowledge-base inference (KBI) [Toutanova et al., 2015]. We first propose a new evaluation protocol that makes comparisons between MF and Tensor Factorization (TF) models fair. We find that this results in a steep drop in MF performance. Our analysis attributes this to the high out-of-vocabulary (OOV) rate of entity pairs in test folds of commonly-used datasets. To alleviate this issue, we propose three extensions to MF. Our best model is a TF-augmented MF model. This hybrid model is robust and obtains strong results across various KBI datasets.
引用
收藏
页码:4122 / 4129
页数:8
相关论文
共 32 条
[31]  
XIE QZ, 2017, ACL, P950, DOI DOI 10.18653/V1/P17-1088
[32]  
Yih S. W.-T., 2014, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), P1568