USFD: Twitter NER with Drift Compensation and Linked Data

TL;DR

This paper presents a Twitter NER system that uses linked data, clustering, and drift compensation to improve entity recognition in social media texts, demonstrating competitive results and detailed analysis.

Contribution

The novel integration of linked data, drift compensation, and unsupervised clustering in a Twitter NER system for the W-NUT 2015 shared task.

Findings

Competitive performance on Twitter NER dataset

Effective drift compensation techniques

Insightful analysis of system components

Abstract

This paper describes a pilot NER system for Twitter, comprising the USFD system entry to the W-NUT 2015 NER shared task. The goal is to correctly label entities in a tweet dataset, using an inventory of ten types. We employ structured learning, drawing on gazetteers taken from Linked Data, and on unsupervised clustering features, and attempting to compensate for stylistic and topic drift - a key challenge in social media text. Our result is competitive; we provide an analysis of the components of our methodology, and an examination of the target dataset in the context of this task.