智能问答QA技术-北大计算机研究所.PDF

文本挖掘技术(2012春) 第十一章： 智能问答 （QA）技术 杨建武 北京大学计算机科学技术研究所 Email:yangjw@ 1 Query Driven vs Answer Driven Information Access  What does LASER stand for?  When did Hitler attack Soviet Union?  Using Google we find documents containing the question itself, no matter whether or not the answer is actually provided.  Current information access is query driven.  Question Answering proposes an answer driven approach to information access. 2 Alternatives to Information Retrieval  Document Retrieval Users submit queries corresponding to their information need,  System returns (voluminous) list of full-length documents, It is the responsibility of the users to find their original information need, within the returned documents.  Question Answering (QA) Users ask fact-based, natural language questions, What is the highest volcano(火山) in Europe?  System returns list of short answers, Under Mount Etna, the highest volcano in Europe, perches the fabulous town … More appropriate for specific information needs. 3 Why Question Answering? From the Caledonian Star in the Mediterranean – September 23, 1990 (): On a beautiful early morning the Caledonian Star approaches Naxos, situated on the east coast of Sicily. As we anchored and put the Zodiacs into the sea we enjoyed the great scenery. Under Mount Etna, the highest volcano in Europe, perches the fabulous town of Taormina. This is the goal for ou