Cross-Lingual Morphological Tagging for Low-Resource Languages

TL;DR

This paper introduces a scalable, projection-based morphological tagging method for low-resource languages that improves parsing accuracy without requiring direct supervision, leveraging cross-lingual information and embedding models.

Contribution

It presents a novel Wsabie-based model for cross-lingual morphological tagging that performs comparably to weakly-supervised baselines and enhances downstream parsing.

Findings

Model performs on par with baseline HMMs

Best results occur between related languages

Improves parser LAS by +0.6 on average

Abstract

Morphologically rich languages often lack the annotated linguistic resources required to develop accurate natural language processing tools. We propose models suitable for training morphological taggers with rich tagsets for low-resource languages without using direct supervision. Our approach extends existing approaches of projecting part-of-speech tags across languages, using bitext to infer constraints on the possible tags for a given word type or token. We propose a tagging model using Wsabie, a discriminative embedding-based model with rank-based learning. In our evaluation on 11 languages, on average this model performs on par with a baseline weakly-supervised HMM, while being more scalable. Multilingual experiments show that the method performs best when projecting between related language pairs. Despite the inherently lossy projection, we show that the morphological tags predicted by our models improve the downstream performance of a parser by +0.6 LAS on average.