IntentsKB: A Knowledge Base of Entity-Oriented Search Intents

TL;DR

This paper presents IntentsKB, a comprehensive knowledge base of entity-oriented search intents, constructed through a pipeline that enables better understanding and utilization of entity-related queries for various applications.

Contribution

It introduces a novel pipeline for building a knowledge base of entity search intents, enabling structured, machine-readable representations of high-level query categories.

Findings

High-quality intent data generated

Effective component-wise and end-to-end performance

Improved support for entity-related search applications

Abstract

We address the problem of constructing a knowledge base of entity-oriented search intents. Search intents are defined on the level of entity types, each comprising of a high-level intent category (property, website, service, or other), along with a cluster of query terms used to express that intent. These machine-readable statements can be leveraged in various applications, e.g., for generating entity cards or query recommendations. By structuring service-oriented search intents, we take one step towards making entities actionable. The main contribution of this paper is a pipeline of components we develop to construct a knowledge base of entity intents. We evaluate performance both component-wise and end-to-end, and demonstrate that our approach is able to generate high-quality data.