TREC 2002 QA at BBN: Answer Selection and Confidence Estimation
نویسندگان
چکیده
We focused on two issues: answer selection and confidence estimation. We found that some simple constraints on the candidate answers can improve a pure IR-based technique for answer selection. We also found that a few simple features derived from the questionanswer pairs can be used for effective confidence estimation. Our results also confirmed findings by Dumais et al, 2002 that the World-Wide Web is a very useful resource for answering TREC-style factoid questions.
منابع مشابه
Answer Selection and Confidence Estimation
We describe BBN’s Question Answering work at TREC 2002. We focus on two issues: answer selection and confidence estimation. We found that some simple constraints on the candidate answers can improve a pure IRbased technique for answer selection. We also found that a few simple features derived from the question-answer pairs can be used for effective confidence estimation. Our results also confi...
متن کاملTREC 2003 QA at BBN: Answering Definitional Questions
For definitional QA, we adopted a hybrid approach that combines several complementary technology components. Information retrieval (IR) was used to retrieve from the corpus the relevant documents for each question. Various linguistic and extraction tools were used to analyze the retrieved texts and to extract various types of kernel facts from which the answer to the question is generated. Thes...
متن کاملQuestion Answering as a Classification Task
In this paper we treat question answering (QA) as a classification problem. Our motivation is to build systems for many languages without the need for highly tuned linguistic modules. Consequently, word tokens and web data are used extensively but no explicit linguistic knowledge is incorporated. A mathematical model for answer retrieval, answer classification and answer length prediction is de...
متن کاملICT Experiments in TREC 11 QA Main Task
This is the second time we participate in the TREC-QA track. We put emphasis on candidate passage ranking and answer matching. As to named entity tagging, we applied the latest version of GATE and did some succeeding work aiming at our goal. This paper presents our methods in detail.
متن کاملThe Pronto QA System at TREC 2007: Harvesting Hyponyms, Using Nominalisation Patterns, and Computing Answer Cardinality
The backbone of the Pronto QA system is linguistically-principled: Combinatory Categorial Grammar is used to generate syntactic analyses of questions and potential answer snippets, and Discourse Representation Theory is employed as semantic formalism to match the meanings of questions and answers. The key idea of the Pronto system is to use semantics to prune answer candidates, thereby exploiti...
متن کامل