Mapping User Intents in Web Search Queries to Types of Commonsense Knowledge

Bachelor thesis (2022)

Authors

X. Huang Electrical Engineering, Mathematics and Computer Science

Contributors

G. He Web Information Systems - EEMCS (mentor)
Ujwal Gadiraju Web Information Systems - EEMCS (mentor)
Luis Cruz Software Engineering - EEMCS (graduation committee member)
Faculty
Electrical Engineering, Mathematics and Computer Science, Electrical Engineering, Mathematics and Computer Science
Copyright: © 2022 Xiaoao Huang
More Info
expand_more

Published Date

28-06-2022

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

Commonsense knowledge is a type of knowledge consisting of facts that humans use every day. Humans make queries in search engines with different user intents, and some of them can be answered by knowledge tuples. Different types of knowledge are stored differently in the knowledge bases. Being aware of the types of commonsense knowledge required to answer the queries can accelerate the process of finding corresponding knowledge for the search engines to give a response to users. For some queries with specific user intents, it is not possible to be answered solely with commonsense knowledge because some analysis and judgment from humans are needed. On the other hand, some queries can be answered with commonsense knowledge tuples and the user intents can have a strong indication of what the knowledge type is required to answer. The research is to look into how to map queries and their user intents to knowledge types and explore the impacts of user intents in the knowledge type classification. There was no existing dataset that had annotations on both user intents and knowledge types. In this work, the described dataset was created. Observations of the created dataset and experiments on three classifiers with accuracy being around 0.99 were conducted. The results show that user intents generally help the classification of the type of commonsense knowledge.