Sparse Coding of Neural Word Embeddings for Multilingual Sequence Labeling
In this paper we propose and carefully evaluate a sequence labeling framework which solely utilizes sparse indicator features derived from dense distributed word representations. The proposed model obtains (near) state-of-the art performance for both part-of-speech tagging and named entity recognition for a variety of languages. Our model relies only on a few thousand sparse coding-derived features, without applying any modification of the word representations employed for the different tasks. The proposed model has favorable generalization properties as it retains over 89.8 tagging accuracy when trained at 1.2 i.e. 150 sentences per language.
READ FULL TEXT