Saarland University Spoken Language Systems at the Slot Filling Task of TAC KBP 2010


For the slot filling task of TAC KBP 2010 we developed as a system a simple pipeline architecture whose main components are a two-stage retrieval module and a relation extraction module. We use word-cluster features in the system as a method of achieving generalization by exploiting raw text. In the relation extraction module we use distant supervision in order to extract training examples from a partially completed knowledge base. The best-ranked run of the full system achieves an F-score of 13.6% on the official test queries.

Extracted Key Phrases

3 Figures and Tables