Relation extraction between entity pairs is an increasingly critical area in natural language processing.Recently the pre-trained bidirectional encoder representation from transformer(BERT)performs excellendy on the t...Relation extraction between entity pairs is an increasingly critical area in natural language processing.Recently the pre-trained bidirectional encoder representation from transformer(BERT)performs excellendy on the text classification or sequence labelling tasks.Here,the high-level syntactic features that consider the dependency between each word and the target entities into the pre-trained language models are incorporated.Our model also utilizes the intermediate layers of BERT to acquire different levels of semantic information and designs multi-granularity features for final relation classification.Our model offers a momentous improvement over the published methods for the relation extraction on the widely used data sets.展开更多
基金National Key Research and Development Program of China,Grant/Award Number:2016YFB1000905the State Key Ptogtam of National Nature Science Foundatioii of China,Grant/Award Numbet:61936001。
文摘Relation extraction between entity pairs is an increasingly critical area in natural language processing.Recently the pre-trained bidirectional encoder representation from transformer(BERT)performs excellendy on the text classification or sequence labelling tasks.Here,the high-level syntactic features that consider the dependency between each word and the target entities into the pre-trained language models are incorporated.Our model also utilizes the intermediate layers of BERT to acquire different levels of semantic information and designs multi-granularity features for final relation classification.Our model offers a momentous improvement over the published methods for the relation extraction on the widely used data sets.