Complex questions that require inferencing and synthesizing information from multiple documents can be seen as a kind of topicoriented, informative multi-document summarization. I...
We describe Joost, our QA system for Dutch, which makes extensive use of dependency relations. We analyzed the full Dutch CLEF QA corpus syntactically and mined it off-line for i...
Gosse Bouma, Jori Mur, Gertjan van Noord, Lonneke ...
The problem of question/answering (Q/A) is to find answers to open-domain questions by searching large collections of documents. Unlike information retrieval systems, very common ...
Mihai Surdeanu, Dan I. Moldovan, Sanda M. Harabagi...
The Question Answering Task requires user interaction. Users can help the system by reformulating the questions, adding information to them or selecting the documents on which the ...
We describe our participation in the WiQA 2006 pilot on question answering using Wikipedia, with a focus on comparing linkbased vs content-based retrieval. Our system currently wor...