Modeling Composite Labels for Neural Morphological Tagging
This work improves morphological tagging for multiple languages, though it is incremental as it builds on existing neural sequence tagging methods.
The authors tackled the problem of neural morphological tagging by modeling morphological tags as composite labels with internal structure, achieving state-of-the-art results on 49 languages.
Neural morphological tagging has been regarded as an extension to POS tagging task, treating each morphological tag as a monolithic label and ignoring its internal structure. We propose to view morphological tags as composite labels and explicitly model their internal structure in a neural sequence tagger. For this, we explore three different neural architectures and compare their performance with both CRF and simple neural multiclass baselines. We evaluate our models on 49 languages and show that the neural architecture that models the morphological labels as sequences of morphological category values performs significantly better than both baselines establishing state-of-the-art results in morphological tagging for most languages.