Modeling Composite Labels for Neural Morphological Tagging

TL;DR

This paper introduces a neural approach that models morphological tags as sequences of internal category values, significantly improving tagging accuracy across 49 languages and establishing new state-of-the-art results.

Contribution

It proposes a novel neural architecture for morphological tagging that explicitly models internal label structure, outperforming traditional monolithic label approaches.

Findings

Significant performance improvements over baselines.

State-of-the-art results for most languages.

Effective modeling of internal label structure.

Abstract

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.