Stefan Kazalski

Learn More
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(More)
We describe the participation of the Saarland University LSV group in the DARPA/NIST TREC 2007 Q&A track with the Alyssa system, using an approach that combines cascaded language-model based information retrieval (LMIR) with data-driven learning methods for answer extraction and ranking. To test the robustness of this approach that was previously proven on(More)
We present the Alyssa QA system which participated in the TAC 2008 Question Answering track. The system consists of two parallel streams: the blogger stream which is used in order to deal with questions which ask for lists of blog authors, and the main stream which processes other opinion questions. We also use a named entity detection component specialized(More)
Although information retrieval techniques have proven to be successful in locating relevant documents, users often prefer to get concise answers to their information need. Question answering systems therefore allow the user to ask natural language questions and provide answers instead of a list of documents. Today, most question answering systems do(More)
In this paper, we discuss the the role of the retrieval component in an TREC style opinion question answering system. Since blog retrieval differs from traditional ad-hoc document retrieval, we need to work on dedicated retrieval methods. In particular we focus on a new query expansion technique to retrieve people’s opinions from blog posts. We(More)
In this paper we describe our participation in the Knowledge Base Population (KBP) track at TAC 2011. The architecture of our slot filling system is the same as last year. We mainly focus on developing a new system for the cross-language entity linking task. We compare the performance of monolingual retrieval and cross-lingual retrieval for entity linking.(More)
  • 1