An Extensive Empirical Evaluation of Character-Based Morphological Tagging for 14 Languages

Abstract

This paper investigates neural characterbased morphological tagging for languages with complex morphology and large tag sets. Character-based approaches are attractive as they can handle rarelyand unseen words gracefully. We evaluate on 14 languages and observe consistent gains over a state-of-the-art morphological tagger across all languages except for English and French, where we match the state-of-the-art. We compare two architectures for computing characterbased word vectors using recurrent (RNN) and convolutional (CNN) nets. We show that the CNN based approach performs slightly worse and less consistently than the RNN based approach. Small but systematic gains are observed when combining the two architectures by ensembling.