Phonologically Aware Neural Model for Named Entity Recognition in Low Resource Transfer Settings

Akash Bharadwaj, David R. Mortensen, Chris Dyer, Jaime Carbonell

Abstract:

Named Entity Recognition is a well established information extraction task with many
state of the art systems existing for a variety of languages. Most systems rely on
language specific resources, large annotated
corpora, gazetteers and feature engineering
to perform well monolingually. In this paper, we introduce an attentional neural model
which only uses language universal phonological character representations with word embeddings to achieve state of the art performance in a monolingual setting using supervision and which can quickly adapt to a new
language with minimal or no data. We demonstrate that phonological character representations facilitate cross-lingual transfer, outperform orthographic representations and incorporating both attention and phonological
features improves statistical efficiency of the
model in 0-shot and low data transfer settings
with no task specific feature engineering in the
source or target language.