TREC 2008 at the University at Buffalo: Legal and Blog Track

17th Text REtrieval Conference

图书情报档案学

Jianqiang Wang ; Ying Sun ; Omar Mukhtar and Rohini Srihari Center of Excellence for Document Analysis and Recognition

PID  :  126370

学科分类：社会科学、人文和艺术（综合）

来源: CEUR

【 摘 要 】

In the TREC 2008, the team from the State University of New York at Buffalo participated in the Legal track and the Blog track. For the Legal track, we worked on the interactive search task using the Webbased Legacy Tobacco Document Library Boolean search system. Our experiment achieved reasonable precision but suffered significantly from low recall. These results, together with the appealing and adjudica tion results, suggest that the concept of document relevance in legal ediscovery deserve further investigation. For the Blog distillation task, our official runs were based on a re duced document model in which only text from several most contentbearing fields were indexed. This approach indeed yielded encouraging retrieval effectiveness while signifi cantly decreasing the index size. We also studied query independence/dependence and linkbased features for finding relevant feeds. For the Blog opinion and polarity tasks, we mainly investigated the usefulness of opinionated words contained in the SentiGI lexicon. Our experiment results showed that the effectiveness of the technique is quite