Hasso-Plattner-Institut
Prof. Dr. Felix Naumann
 

16.01.2021

Paper accepted at WWW 2021

Michael Loster, Davide Mottin, Paolo Papotti, Felix Naumann, Jan Ehmueller, Benjamin Feldmann

We are proud to announce that our research paper "Few-Shot Knowledge Validation using Rules" has been accepted for presentation at the Web Conference 2021 (WWW2021).
The paper is the result of our cooperation with Davide Mottin (Aarhus University - Denmark) and Paolo Papotti (EURECOM - France) and represents the outcome of a successful collaboration across three different countries. Our research results will be presented at WWW 2021. For more information on the Web Conference 2021, please visit: https://www2021.thewebconf.org/.
The key points of our work can be summarized as follows:

Abstract

Knowledge graphs (KGs) form the basis of modern intelligent search systems -- their network structure helps with the semantic reasoning and interpretation of complex tasks. A KG is a highly dynamic structure in which facts are continuously updated, added, and removed. A typical approach to ensure data quality in the presence of continuous changes is to apply logic rules. These rules are automatically mined from the data using frequency-based approaches. As a result, these approaches depend on the data quality of the KG and are susceptible to errors and incompleteness. To address these issues, we propose COLT, a few-shot rule-based knowledge validation framework that enables the interactive quality assessment of logic rules. It evaluates the quality of any rule by asking a user to validate only a few facts entailed by such rule on the KG. We formalize the problem as learning a validation function over the rule's outcomes and study the theoretical connections to the generalized maximum coverage problem. Our model obtains (i) an accurate estimate of the quality of a rule with fewer than 20 user interactions and (ii) 75% quality (F1) with 5% annotations in the task of validating facts entailed by any rule.