We present a new method for information retrieval using hidden Markov models (HMMs) and relate our experience with this system on the TREC-7 ad hoc task. We develop a general framework for incorporating multiple word generation mechanisms within the same model. We then demonstrate that an extremely simple realization of this model substantially outperforms tf :idf ranking on both the TREC-6 and...

The human thymus is required for establishment of a T-cell pool in fetal life, but postnatal thymectomy is not known to cause immunodeficiency. T-cell emigration from thymus (thymic recent emigrants [TRECs]) is a continuous thymic-dependent process. We studied TREC levels pre- and post-partial thymectomy in children undergoing cardiac surgery. TRECs were quantitated by real-time PCR in peripher...

Recent advances in characterizing thymic function confirm the importance of thymus to T-cell diversity in the periphery of both children and adults during both health and disease. Lack of a marker to identify human recent thymic emigrants (RTEs) is the biggest hurdle to accurately characterizing and quantifying thymic output. T-cell receptor excision circles (TRECs) are used as an assay to meas...

This paper explores information retrieval system variability and takes advantage of the fact two systems can retrieve different documents for a given query. More precisely, our approach is based on data fusion (fusion of system results) by taking into account local performances of each system. Our method considers the relevance of the very first documents retrieved by different systems and from...

Nine teams participated in the TREC-2002 cross-language information retrieval track, which focused on retrieving Arabic language documents based on 50 topics that were originally prepared in English. Arabic translations of the topic descriptions were also made available to facilitate monolingual Arabic runs. This was the second year in which a large Arabic document collection was available. Thr...

Benchmark tasks are a powerful method for advancing the state of the art in a field. The music information retrieval community recently acknowledged the utility of such tasks by resolving to create an evaluation framework for music information retrieval (MIR) tasks and music digital libraries (MDL). This paper describes the processes used in the Text REtrieval Conference (TREC) evaluations to c...

We introduce our participation of the TREC Relevance Feedback(RF) TRACK in 2009. The RF09 TRACK is focused on the explicit relevant feedback, where a few relevant and irrelevant documents are available to each query. Our system is implemented under the framework of probabilistic language model. We apply the constrained clustering on the top returned documents and extract the expanded words to r...

Ad-hoc queries are usually short, of perhaps two to ten terms. However, in previous rounds of TREC we have concentrated on obtaining optimal performance for the long TREC topics. In this paper we investigate the behaviour of similarity measures on short queries, and show experimentally that two successful measures|which give similar, good performance on long TREC topics|do not work well for sho...

We consider Information Retrieval evaluation, especially at Trec with the trec eval program. It appears that systems obtain scores regarding not only the relevance of retrieved documents, but also according to document names in case of ties (i.e., when they are retrieved with the same score). We consider this tie-breaking strategy as an uncontrolled parameter influencing measure scores, and arg...

We present evaluation results of a generative probabilistic image retrieval model using ‘easy data’. Previous research into our model’s retrieval effectiveness has used the test collection developed at TREC’s Video Track, but as discussed in detail in [17], its search task has been too difficult to measure actual performance of the retrieval model. The ‘easy data’ experiments presented here eva...