English

The IMS-CUBoulder System for the SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completion

Computation and Language 2020-05-27 v1 Machine Learning

Abstract

In this paper, we present the systems of the University of Stuttgart IMS and the University of Colorado Boulder (IMS-CUBoulder) for SIGMORPHON 2020 Task 2 on unsupervised morphological paradigm completion (Kann et al., 2020). The task consists of generating the morphological paradigms of a set of lemmas, given only the lemmas themselves and unlabeled text. Our proposed system is a modified version of the baseline introduced together with the task. In particular, we experiment with substituting the inflection generation component with an LSTM sequence-to-sequence model and an LSTM pointer-generator network. Our pointer-generator system obtains the best score of all seven submitted systems on average over all languages, and outperforms the official baseline, which was best overall, on Bulgarian and Kannada.

Cite

@article{arxiv.2005.12411,
  title  = {The IMS-CUBoulder System for the SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completion},
  author = {Manuel Mager and Katharina Kann},
  journal= {arXiv preprint arXiv:2005.12411},
  year   = {2020}
}
R2 v1 2026-06-23T15:48:19.693Z