作者: Cosmin Adrian Bejan , Paul Morarescu , Sanda Harabagiu
DOI:
关键词:
摘要: This paper presents a new method for extracting meaningful relations from unstructured natural language sources. The is based on information made available by shallow semantic parsers. Semantic was used (1) to enhance dependency tree kernel; and (2) build structures enhanced relation extraction several classifiers. In our experiments the quality of extracted surpassed results kernel-based models employing only class information.