Learning Character-level Representations for Part-of-Speech Tagging

A deep neural network is proposed that learns character-level representation of words and associate them with usual word representations to perform POS tagging and produces state-of-the-art POS taggers for two languages.

Abstract

Distributed word representations have recently been proven to be an invaluable resource for NLP. These representations are normally learned using neural networks and capture syntactic and semantic information about words. Informa-tion about word morphology and shape is nor-mally ignored when learning word representa-tions. However, for tasks like part-of-speech tag-ging, intra-word information is extremely use-ful, specially when dealing with morphologically rich languages. In this paper, we propose a deep neural network that learns character-level repre-sentation of words and associate them with usual word representations to perform POS tagging. Using the proposed approach, while avoiding the use of any handcrafted feature, we produce state-of-the-art POS taggers for two languages: En-glish, with 97.32 % accuracy on the Penn Tree-bank WSJ corpus; and Portuguese, with 97.47% accuracy on the Mac-Morpho corpus, where the latter represents an error reduction of 12.2 % on the best previous known result. 1.