The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection

TL;DR

This paper reports on the SIGMORPHON 2019 shared task, which focused on cross-lingual transfer learning for morphological inflection and contextual analysis, demonstrating improvements over baselines across multiple languages.

Contribution

It introduces new challenges for cross-lingual transfer of morphological inflection and contextual lemmatization, with all submissions outperforming existing baselines.

Findings

All teams improved accuracy over baselines for inflection.

All teams improved on state-of-the-art for contextual analysis.

Neural models showed consistent gains across tasks.

Abstract

The SIGMORPHON 2019 shared task on cross-lingual transfer and contextual analysis in morphology examined transfer learning of inflection between 100 language pairs, as well as contextual lemmatization and morphosyntactic description in 66 languages. The first task evolves past years' inflection tasks by examining transfer of morphological inflection knowledge from a high-resource language to a low-resource language. This year also presents a new second challenge on lemmatization and morphological feature analysis in context. All submissions featured a neural component and built on either this year's strong baselines or highly ranked systems from previous years' shared tasks. Every participating team improved in accuracy over the baselines for the inflection task (though not Levenshtein distance), and every team in the contextual analysis task improved on both state-of-the-art neural and non-neural baselines.