A Knowledge Graph Based Solution for Entity Discovery and Linking in Open-Domain Questions

TL;DR

This paper presents a knowledge graph based system for entity discovery and linking in short questions, combining retrieval and CRF methods for improved recall and precision, achieving competitive results.

Contribution

It introduces a novel ensemble approach for question entity discovery and a ranking-based entity linking method tailored for short texts.

Findings

Achieved 64.44% F1 score in question entity discovery

Attained 64.86% accuracy in entity linking

Ranked 2nd in official QEDL evaluation

Abstract

Named entity discovery and linking is the fundamental and core component of question answering. In Question Entity Discovery and Linking (QEDL) problem, traditional methods are challenged because multiple entities in one short question are difficult to be discovered entirely and the incomplete information in short text makes entity linking hard to implement. To overcome these difficulties, we proposed a knowledge graph based solution for QEDL and developed a system consists of Question Entity Discovery (QED) module and Entity Linking (EL) module. The method of QED module is a tradeoff and ensemble of two methods. One is the method based on knowledge graph retrieval, which could extract more entities in questions and guarantee the recall rate, the other is the method based on Conditional Random Field (CRF), which improves the precision rate. The EL module is treated as a ranking problem and Learning to Rank (LTR) method with features such as semantic similarity, text similarity and entity popularity is utilized to extract and make full use of the information in short texts. On the official dataset of a shared QEDL evaluation task, our approach could obtain 64.44% F1 score of QED and 64.86% accuracy of EL, which ranks the 2nd place and indicates its practical use for QEDL problem.