Research On Key Techniques Of Patten Knowledge Based Question Answering

More and more information are now available in machine-readable form. It makes the technology of Information Retrieval and Information Extraction more important for effectively looking up and making use of these information. But there exist some shortcomings with traditional search engines. The users' requirements are expressed with the keywords, which may result in the loss of semantic information. Search engine returns the relevant links or document lists, and users need more efforts to acquire the needed information. The research of Question Answering is to resolve these problems. It accepts the questions in natural language that denoting user requirements and returns the exact answers after analysing the document information. This is a challenging task to computers although it seems simple. We have a deep research on the technique of question answering based on this premise.This dissertation focuses on the key techniques of pattern knowledge based question answering. We design and implement the question answering system and take part in the evaluation of Text Retrieval Conference. We also apply the pattern matching technique to a new related research area Reading Comprehension, and a satisfied result is acquired.The key task to implement the pattern matching technique is to construct a perfect pattern knowledge base. We put forward a novel question classification hierarchy which is based on answer type and question pattern. It retains the semantic and structured information of questions. We make use of the questions on TREC as our training and test data. The answer patterns to different question types are studied and evaluated automatically.We have implemented pattern learning to questions with complex structure. It is more effective and reliable to extract the correct answer with answer patterns containing multiple question terms. This cannot be covered by simple answer patterns. For higher precision, we give semantic restriction to candidate answers that are extracted by answer patterns.We adopt generalization strategy to answer patterns using named entity information. It makes the answer patterns have better extending ability. The constituent elements of answer pattern contain both morphological and semantic information with better robustness.We evaluate all the answer patterns by the concept of Confidence and Support, which are borrowed from data mining. Answer patterns with higher confidence lead to choose the answer with greater reliability.In our Reading Comprehension system, we make use of the synonymy information of WordNet and adopt the pattern matching technique and context assistance technique. The system performance gets an obvious enhancement and precedes previous results.