Ranking Entity Based on Both of Word Frequency and Word Sematic Features

TL;DR

This paper presents a ranking method for entity search that combines word frequency and semantic features, demonstrating high performance in Baidu Cup 2016 Challenge across multiple entity types.

Contribution

The paper introduces a novel set of similarity features based on word frequency and semantics, along with a ranking architecture that achieved top results in a competitive challenge.

Findings

Achieved first place in Baidu Cup 2016 Challenge for entity search

Developed effective similarity features combining frequency and semantics

Demonstrated superior ranking performance across multiple entity types

Abstract

Entity search is a new application meeting either precise or vague requirements from the search engines users. Baidu Cup 2016 Challenge just provided such a chance to tackle the problem of the entity search. We achieved the first place with the average MAP scores on 4 tasks including movie, tvShow, celebrity and restaurant. In this paper, we propose a series of similarity features based on both of the word frequency features and the word semantic features and describe our ranking architecture and experiment details.