Query Understanding via Entity Attribute Identification

TL;DR

This paper introduces the task of entity attribute identification to improve query understanding in semantic search, proposing two models and demonstrating significant performance gains on a human-annotated dataset.

Contribution

It presents the novel task of entity attribute identification and develops two models, advancing query understanding in semantic search systems.

Findings

Proposed two models for entity attribute identification.

Developed a human-annotated test collection.

Achieved significant improvements over baseline methods.

Abstract

Understanding searchers' queries is an essential component of semantic search systems. In many cases, search queries involve specific attributes of an entity in a knowledge base (KB), which can be further used to find query answers. In this study, we aim to move forward the understanding of queries by identifying their related entity attributes from a knowledge base. To this end, we introduce the task of entity attribute identification and propose two methods to address it: (i) a model based on Markov Random Field, and (ii) a learning to rank model. We develop a human annotated test collection and show that our proposed methods can bring significant improvements over the baseline methods.