Copenhagen at CoNLL--SIGMORPHON 2018: Multilingual Inflection in Context with Explicit Morphosyntactic Decoding

TL;DR

This paper presents Copenhagen's multilingual system for context-aware morphological inflection, achieving top accuracy in the CoNLL--SIGMORPHON 2018 shared task by leveraging a wide context window, multi-task learning, and multilingual training.

Contribution

It introduces a novel encoder-decoder model with three key innovations for inflection in context, significantly improving performance over previous methods.

Findings

Achieved 49.87% accuracy in the shared task

Outperformed previous context-agnostic models

Demonstrated effectiveness of multilingual training

Abstract

This paper documents the Team Copenhagen system which placed first in the CoNLL--SIGMORPHON 2018 shared task on universal morphological reinflection, Task 2 with an overall accuracy of 49.87. Task 2 focuses on morphological inflection in context: generating an inflected word form, given the lemma of the word and the context it occurs in. Previous SIGMORPHON shared tasks have focused on context-agnostic inflection---the "inflection in context" task was introduced this year. We approach this with an encoder-decoder architecture over character sequences with three core innovations, all contributing to an improvement in performance: (1) a wide context window; (2) a multi-task learning approach with the auxiliary task of MSD prediction; (3) training models in a multilingual fashion.