The CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection

TL;DR

This paper reports on the CoNLL--SIGMORPHON 2018 shared task, which involved developing neural systems for morphological inflection across 103 languages and inferring words in sentential context, highlighting advances and challenges.

Contribution

It introduces a large-scale multilingual morphological inflection shared task with a new context-based inflection challenge, expanding on previous work and providing a benchmark for neural approaches.

Findings

Most systems improved over baselines in low-resource settings for inflection.

The sentential context inflection task was notably more difficult for participants.

Neural methods dominated submissions, building on previous top systems.

Abstract

The CoNLL--SIGMORPHON 2018 shared task on supervised learning of morphological generation featured data sets from 103 typologically diverse languages. Apart from extending the number of languages involved in earlier supervised tasks of generating inflected forms, this year the shared task also featured a new second task which asked participants to inflect words in sentential context, similar to a cloze task. This second task featured seven languages. Task 1 received 27 submissions and task 2 received 6 submissions. Both tasks featured a low, medium, and high data condition. Nearly all submissions featured a neural component and built on highly-ranked systems from the earlier 2017 shared task. In the inflection task (task 1), 41 of the 52 languages present in last year's inflection task showed improvement by the best systems in the low-resource setting. The cloze task (task 2) proved to be difficult, and few submissions managed to consistently improve upon both a simple neural baseline system and a lemma-repeating baseline.