Neural Factor Graph Models for Cross-lingual Morphological Tagging

TL;DR

This paper introduces a neural factor graph model for cross-lingual morphological tagging that relaxes the strict tag set overlap assumption, enabling better information sharing and improved accuracy across languages.

Contribution

It proposes a neural factorial CRF model that captures relationships between tags and handles unseen tags, advancing cross-lingual morphological analysis.

Findings

Outperforms existing cross-lingual tagging methods

Effectively models relationships between morphological tags

Improves accuracy on low-resource languages

Abstract

Morphological analysis involves predicting the syntactic traits of a word (e.g. {POS: Noun, Case: Acc, Gender: Fem}). Previous work in morphological tagging improves performance for low-resource languages (LRLs) through cross-lingual training with a high-resource language (HRL) from the same family, but is limited by the strict, often false, assumption that tag sets exactly overlap between the HRL and LRL. In this paper we propose a method for cross-lingual morphological tagging that aims to improve information sharing between languages by relaxing this assumption. The proposed model uses factorial conditional random fields with neural network potentials, making it possible to (1) utilize the expressive power of neural network representations to smooth over superficial differences in the surface forms, (2) model pairwise and transitive relationships between tags, and (3) accurately generate tag sets that are unseen or rare in the training data. Experiments on four languages from the Universal Dependencies Treebank demonstrate superior tagging accuracies over existing cross-lingual approaches.