Name ambiguity is one of the most common problems in natural language processing and has raised an urgent demand for efficient, high-quality named entity disambiguation methods. In recent years, with the emergency of knowledge base such as Wikipedia, there are large amount of method proposed based on knowledge base. Named Entity Disambiguation (NED) refers to the task of resolving multiple named entity mentions in a document to their correct references in a knowledge base. The main difficulty in NED is ambiguity in the meaning of entity mentions. In this paper, we combine local context and global hyperlink structure from Wikipedia to compensate for the limitations of only using one of the methods. The experimental results show that the two models of context, namely, words in the context and hyperlink pathways to other entities in the context, are complementary. Results are not tuned to any of the datasets, showing that it is robust to out-of-domain scenarios, and that further improvements are possible.
展开▼
