# CMU-01 at the SIGMORPHON 2019 Shared Task on Crosslinguality and Context in Morphology

## TL;DR

This paper introduces a hierarchical neural CRF model for morphological analysis and lemmatization in context, leveraging multi-lingual transfer learning to improve performance on under-resourced languages in the SIGMORPHON 2019 shared task.

## Contribution

It presents a novel multi-lingual transfer training approach combined with a hierarchical neural CRF model for morphological analysis in context.

## Key findings

- Effective transfer learning improves results on low-resource languages.
- Hierarchical neural CRF achieves competitive performance in morphological tasks.
- Multi-lingual training enhances model generalization across languages.

## Abstract

This paper presents the submission by the CMU-01 team to the SIGMORPHON 2019 task 2 of Morphological Analysis and Lemmatization in Context. This task requires us to produce the lemma and morpho-syntactic description of each token in a sequence, for 107 treebanks. We approach this task with a hierarchical neural conditional random field (CRF) model which predicts each coarse-grained feature (eg. POS, Case, etc.) independently. However, most treebanks are under-resourced, thus making it challenging to train deep neural models for them. Hence, we propose a multi-lingual transfer training regime where we transfer from multiple related languages that share similar typology.