Portal de Periódicos da CAPES

Stanford-UBC at TAC-KBP

2009; Masaryk University; Linguagem: Inglês

1201-561X

Eneko Agirre, Anne Lynn S. Chang, Daniel Jurafsky, Christopher D. Manning, Valentin I. Spitkovsky, Eric Yeh,

Text and Document Classification Technologies

This paper describes the joint Stanford-UBC knowledge base population system. We developed several entity linking systems based on frequencies of backlinks, training on contexts of anchors, overlap of context with the text of the entity in Wikipedia, and both heuristic and supervised combinations. Our combined systems performed better than the individual components, which situates our runs better than the median of participants. For slot filling, we implemented a straightforward distant supervision system, trained using snippets of the document collection containing both entity and filler from Wikipedia infoboxes. In this case our results are below the median.