RESLVE: Leveraging User Interest to Improve Entity Disambiguation on Short Text

TL;DR

This paper introduces RESLVE, a novel approach that leverages user interest modeling and Wikipedia to significantly improve entity disambiguation accuracy in short, user-generated social media texts.

Contribution

The paper presents a new user-interest based model for NED that outperforms existing state-of-the-art methods on social media data.

Findings

Achieves substantial accuracy improvements over existing NED methods.

Effective in disambiguating entities in short social media texts.

Demonstrates robustness across Twitter, YouTube, and Flickr data.

Abstract

We address the Named Entity Disambiguation (NED) problem for short, user-generated texts on the social Web. In such settings, the lack of linguistic features and sparse lexical context result in a high degree of ambiguity and sharp performance drops of nearly 50% in the accuracy of conventional NED systems. We handle these challenges by developing a model of user-interest with respect to a personal knowledge context; and Wikipedia, a particularly well-established and reliable knowledge base, is used to instantiate the procedure. We conduct systematic evaluations using individuals' posts from Twitter, YouTube, and Flickr and demonstrate that our novel technique is able to achieve substantial performance gains beyond state-of-the-art NED methods.