The NYU-CUBoulder Systems for SIGMORPHON 2020 Task 0 and Task 2

TL;DR

This paper presents transformer-based models, including a pointer-generator variant, for morphological inflection and paradigm completion, achieving top-tier results in SIGMORPHON 2020 tasks.

Contribution

Introduction of transformer and pointer-generator transformer models for morphological tasks, demonstrating improved performance on diverse languages.

Findings

Transformer model achieved competitive results in Task 0.

Pointer-generator model improved copying of characters from lemmas.

System ranked 6th in Task 0 and 2nd in Task 2.

Abstract

We describe the NYU-CUBoulder systems for the SIGMORPHON 2020 Task 0 on typologically diverse morphological inflection and Task 2 on unsupervised morphological paradigm completion. The former consists of generating morphological inflections from a lemma and a set of morphosyntactic features describing the target form. The latter requires generating entire paradigms for a set of given lemmas from raw text alone. We model morphological inflection as a sequence-to-sequence problem, where the input is the sequence of the lemma's characters with morphological tags, and the output is the sequence of the inflected form's characters. First, we apply a transformer model to the task. Second, as inflected forms share most characters with the lemma, we further propose a pointer-generator transformer model to allow easy copying of input characters. Our best performing system for Task 0 is placed 6th out of 23 systems. We further use our inflection systems as subcomponents of approaches for Task 2. Our best performing system for Task 2 is the 2nd best out of 7 submissions.