Learning NER from Experts

This paper was accepted to IES-2015 in Bangkok, Thailand.

Abstract

Named Entity Recognition (NER) is a foundational technology for systems designed to process Natural Language documents. However, many existing state-of-the-art systems are difficult to integrate into commercial settings (due their monolithic construction, licensing constraints, or need for corpuses, for example). In this work, a new NER system is described that uses the output of existing systems over large corpuses as its training set, ultimately enabling labelling with (i) better F1 scores; (ii )higher labelling speeds; and (iii) no further dependence on the external software.

Poster Version

This version was actually shown as a poster as part of a 'local researchers' competition at the Nvidia ASEAN GPU conference in 2015, where it won 2nd prize : a Titan X (Maxwell) Nvidia GPU!

Conference Presentation

Here are the Presentation slides that I presented for the paper at IES-2015 in Bangkok, Thailand.

If there are any questions about the presentation please ask below, or contact me using the details given on the slides themselves.

Link to Paper

Direct link to PDF on author website - (as allowed by Springer copyright rules)

And the Springer BiBTeX entry:

@incollection{andrews2016named,
  title={Named Entity Recognition Through Learning from Experts},
  author={Andrews, Martin},
  booktitle={Intelligent and Evolutionary Systems},
  pages={281--292},
  year={2016},
  publisher={Springer}
}