Omni-word Feature and Soft Constraint for Chinese Relation Extraction

Yanping Chen, Qinghua Zheng, Wei Zhang
2014 Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
Chinese is an ancient hieroglyphic. It is inattentive to structure. Therefore, segmenting and parsing Chinese are more difficult and less accurate. In this paper, we propose an Omniword feature and a soft constraint method for Chinese relation extraction. The Omni-word feature uses every potential word in a sentence as lexicon feature, reducing errors caused by word segmentation. In order to utilize the structure information of a relation instance, we discuss how soft constraint can be used to
more » ... apture the local dependency. Both Omni-word feature and soft constraint make a better use of sentence information and minimize the influences caused by Chinese word segmentation and parsing. We test these methods on the ACE 2005 RDC Chinese corpus. The results show a significant improvement in Chinese relation extraction, outperforming other methods in F-score by 10% in 6 relation types and 15% in 18 relation subtypes.
doi:10.3115/v1/p14-1054 dblp:conf/acl/ChenZZ14 fatcat:cga4jamk55dvdhucmb4cwubssy