Lattice: Data Adaptation for Named Entity Recognition on Tweets with Features-Rich CRF

Abstract

This article describes our CRF named entity extractor for Twitter data. We first discuss some specificities of the task, with an example found in the training data. Then we present how we built our CRF model, especially the way features were defined. The results of these first experiments are given. We also tested our model with dev 2015 data and we describe the procedure we have used to adapt older Twitter data to the data available for this 2015 shared task. Our final results for the task are discussed.