Learning Multi-granular Features for Harvesting Knowledge from Free Text

摘要

Extracting entities and their relations expressed in free text is essential to correct and populate knowledge graphs. Traditional meth-ods assume that only the information of entities benefits the extraction of relations. They view this task as a two-step task, named entity recog-nition (NER) and relation classification (RC). However, the inadequate use of information and the error propagation problem constrain meth-ods following this pipeline fashion. Joint extraction methods are pro-posed to incorporate useful interaction information between the two tasks for improvement, which solve NER and RC simultaneously. Although they have been proved to be superior to pipeline models, their performance is still far from satisfaction. In this paper, we try to combine the idea of data-driven granular cognitive computing and deep learning in joint extraction task. Accordingly, a neural-based joint extraction model named Joint extraction with Multi-granularity Context (JMC) is pro-posed. It explores the multi-granularity context of natural language sen-tences and uses neural networks to learn representations of these context automatically. Experiments results on NYT, a large data set produced by the distant supervision technique, show that JMC achieves comparative results to state-of-the-art methods.