IntentsKB: A Knowledge Base of Entity-Oriented Search Intents
This work addresses the need for structured, actionable entity intents in applications like entity cards and query recommendations, representing an incremental advancement in knowledge base construction.
The paper tackles the problem of constructing a knowledge base of entity-oriented search intents, resulting in a pipeline that generates high-quality data as demonstrated through component-wise and end-to-end evaluation.
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.