Analysis of Named Entity Recognition and Linking for Tweets

TL;DR

This paper investigates the challenges of named entity recognition and linking in tweets, analyzing the robustness of existing systems on noisy, short texts and identifying key areas for improvement.

Contribution

It introduces a new Twitter entity disambiguation dataset and provides an empirical analysis of current NER and linking systems on tweet data.

Findings

State-of-the-art systems struggle with noisy tweet data

Main errors stem from context ambiguity and noise

Identifies key challenges for future research

Abstract

Applying natural language processing for mining and intelligent information access to tweets (a form of microblog) is a challenging, emerging research area. Unlike carefully authored news text and other longer content, tweets pose a number of new challenges, due to their short, noisy, context-dependent, and dynamic nature. Information extraction from tweets is typically performed in a pipeline, comprising consecutive stages of language identification, tokenisation, part-of-speech tagging, named entity recognition and entity disambiguation (e.g. with respect to DBpedia). In this work, we describe a new Twitter entity disambiguation dataset, and conduct an empirical analysis of named entity recognition and disambiguation, investigating how robust a number of state-of-the-art systems are on such noisy texts, what the main sources of error are, and which problems should be further investigated to improve the state of the art.