Using Structured Queries for Keyword Information Retrieval

An increasingly important class of keyword search tasks are those where users are looking for a specific piece of information buried within a few documents in a large collection. Examples include searching for someone’s phone number, the schedule for a meeting, or a package tracking URL, within a personal email collection. We refer to such tasks as “precision-oriented search tasks”. While modern information extraction techniques can be used to extract the concepts involved in these tasks (persons, phone numbers, schedules, etc.), since users only provide keywords as input, the problem of identifying the documents that contain the information of interest remains a challenge. In this paper, we propose a solution to this problem based on the concept of automatically generating “interpretations” of keyword queries. Interpretations are precise structured queries, over the extracted concepts, that model the real intent behind a keyword query. We formalize the notion of interpretations and address the challenges in identifying the most likely interpretations for a given keyword query. We validate the benefits of our approach by presenting results both from a user study and experimental comparisons against an alternative approach.