Robust Lexical Features for Improved Neural Network Named-Entity Recognition

Understand

Neural network approaches to Named-Entity Recognition reduce the need for carefully hand-crafted features.

• While some features do remain in state-of-the-art systems, lexical features have been mostly discarded, with the exception of gazetteers.
• In this work, we show that this is unfair: lexical features are actually quite useful.
• We propose to embed words and entity types into a low-dimensional vector space we train from annotated data produced by distant supervision thanks to Wikipedia.