FDUQA on TREC 2005 QA Track
نویسندگان
چکیده
In this year’s QA Track, we participant in the main and document ranking task and do not take part in the relation task. We put the most effort in factoid and definition questions, and very little on list questions and document ranking task. For factoid questions, we use three QA systems: system 1, system 2 and system 3. System 1 is very similar to our last year’s system [Wu et al, 2004] except two main modifications. One is adding an answer validation-feedback scheme. The other is an improved answer projection module. System 2 is a classic QA system that does not use Web. System 3 is a pattern-based system that we used in TREC 2002 evaluation. The main contribution for factoid question is two improvements for Web-based QA system and the system combination. For definition question, we attempt to utilize both the existing definitions in the Web knowledge bases and the automatically generated structured patterns. Effective methods are adopted to make full use of these resources, and they promise high quality response to definition questions. For list questions, we use a pattern-based method to find more answers other than those found in the processing of factoid question. For document ranking task, we only collect the outputs from document searching or answer projection module. In the following, Section 2, 3, 4 will describe our algorithms to factoid, list and definition questions separately. Section 5 will present our results in TREC 2005.
منابع مشابه
FDUQA on TREC 2006 QA Track
In this year’s QA Track, we participant in the main task and do not take part in the ciQA task. The main task is essentially the same as the single task from 2004, in that the test set consists of a set of question series where each series asks for information regarding a particular target. In order to better answer the questions in the series, we try to improve our anaphora resolution within q...
متن کاملFDUQA on TREC2003 QA task
It is the fourth time that we take part in the QA track. Our system, FDUQA, is based on our previous system (Wu et al, 2002). FDUQA includes an offline part and an online part. We make great efforts on the online part while leaving the offline part unchanged. We have tried many natural language processing techniques, and incorporated many sources of world knowledge, including Web. A novel Query...
متن کاملFDUQA on TREC 2004 QA Track
In this year’s QA Track, we process factoid questions in a way that is slightly different from our previous system [1]. The most significant difference is that we developed a new answer type category, and trained a classifier for answer type classification. To answer list questions, we use a pattern-based method to find more answers other than those found in the processing of factoid question. ...
متن کاملThe Evaluation of Question Answering Systems: Lessons Learned from the TREC QA Track
The TREC question answering (QA) track was the first large-scale evaluation of open-domain question answering systems. In addition to successfully fostering research on the QA task, the track has also been used to investigate appropriate evaluation methodologies for question answering systems. This paper gives a brief history of the TREC QA track, motivating the decisions made in its implementa...
متن کامل