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

Abstract

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 Fscore of 13.6% on the official test queries.

Extracted Key Phrases

2 Figures and Tables

Cite this paper

@inproceedings{Chrupala2010SaarlandUS, title={Saarland University Spoken Language Systems at the Slot Filling Task of TAC KBP 2010}, author={Grzegorz Chrupala and Saeedeh Momtazi and Michael Wiegand and Stefan Kazalski and Fang Xu and Benjamin Roth and Alexandra Balahur and Dietrich Klakow}, booktitle={TAC}, year={2010} }