Utilizing Passages in Fusion-based Document Retrieval

Abstract

The usage of passage-level information has been successfully demonstrated in many core IR tasks, and among such tasks, the task of passage-based document retrieval. In this work, we study the merits of utilizing similar information for the fusion-based document retrieval task. Overall, we show that such information can be highly useful for this task as well. To this end, we propose three passage-based fusion methods and show that their performance can transcend that of strong document-level fusion methods.