TREC-10 Experiments at KAIST: Batch Filtering and Question Answering

TREC-9 Experiments at KAIST: QA, CLIR and Batch Filtering

Microsoft Cambridge at TREC-9: Filtering Track

Apart from a short description of our Query Track contribution, this report is concerned with the Adaptive Filtering track only. There is a separate report in this volume [1] on the Microsoft Research Cambridge participation in QA track. A number of runs were submitted for the Adaptive Filtering track, on all tasks (adaptive filtering, batch filtering and routing; three separate query sets; two...

Further Analysis of Whether Batch and User Evaluations Give the Same Results with a Question-Answering Task

In the TREC-8 Interactive Track, our results indicated that the better performance obtained in batch searching evaluation do not translate into better performance by users in an instance recall task. This year we pursued this investigation further by performing the same experiments using the new questionanswering task adopted in the TREC-9 Interactive Track. Our results once again show that bet...

TREC-8 Experiments at Maryland: CLIR, QA and Routing

The University of Maryland team participated in four aspects of TREC-8: the ad hoc retrieval task, the main task in the cross-language retrieval (CLIR) track, the question answering track, and the routing task in the filtering track. The CLIR method was based on Pirkola’s method for Dictionary-based Query Translation, using freely available dictionaries. Broad-coverage parsing and rule-based ma...

Utilizing Co-Occurrence of Answers in Question Answering

In this paper, we discuss how to utilize the co-occurrence of answers in building an automatic question answering system that answers a series of questions on a specific topic in a batch mode. Experiments show that the answers to the many of the questions in the series usually have a high degree of co-occurrence in relevant document passages. This feature sometimes can’t be easily utilized in a...