Monday, 6 March, 2017 - 13:30 to 15:00

Neural Network Based Named Entity Recognition

We present the recent artificial neural network based methods for named entity
recognition (NER, the identification and classification of proper names in
text). We briefly introduce the task and data, and quickly skimming through
related work (Ratinov and Roth, 2009), we focus on recent advances in the field
of artificial neural networks - word embeddings and character-level embeddings.
Previous knowledge of these concepts is not necessary, we explain them in the
context of NER. We present both the current English (Lample et al., 2016) and
Czech (Strakova et al., 2016) state of the art.