TREC 2004 Genomics Track Experiments at IUB

13th Text REtrieval Conference

图书情报档案学

Kazuhiro Seki ; James C. Costello ; Vasanth R. Singan ; Javed Mostafa

PID  :  122453

学科分类：社会科学、人文和艺术（综合）

来源: CEUR

【 摘 要 】

This paper describes the methods we developed for the three tasks of the TREC Genomics Track, i.e., ad hoc retrieval, triage, and annotation tasks. For the ad hoc retrieval task, we used the classic vector space model and studied the use of query expansion and pseudo relevance feedback. Our submitted runs obtained a MAP of 0.183. For the triage task, we adopted a nave Bayes classifier trained on MeSH terms and used gene names as filters to rule out false positives. The obtained normalized utility score was 0.435. For the annotation task, we focused on document representation and ap plied a variant of the kNN classifiers. One of our sub mitted runs produced an F1 score of 0.561, ranking first