An Entity-Level Approach to Information Extraction

We present a generative model of template-filling in which coreference resolution and role assignment are jointly determined. Underlying template roles nerate abstract entities, which in turn generate concrete textual mentions. On the standard corporate acquisitions dataset, joint resolution in our entity-level model reduces error over a mention-level discriminative approach by up to 20%.

• Type: Journal
• Year: 2010
• Where: ACL
• Authors: Aria Haghighi, Dan Klein
• Keywords: ACL 2010, Computational Linguistics, Concrete Textual Mentions, Mention-level Discriminative Approach, Standard Corporate Acquisitions