LemMED: Fast and Effective Neural Morphological Analysis with Short Context Windows

TL;DR

LemMED is a character-level encoder-decoder model for efficient morphological analysis that uses minimal local context, achieving competitive results without external resources or global context modeling.

Contribution

The paper introduces LemMED, a novel character-level model that performs joint lemmatization and tagging using only local context, simplifying and speeding up morphological analysis.

Findings

LemMED ranks 5th in the SIMGMORPHON-2019 shared task.

Using just one word of context improves performance over larger contexts.

LemMED outperforms models requiring external resources and global context.

Abstract

We present LemMED, a character-level encoder-decoder for contextual morphological analysis (combined lemmatization and tagging). LemMED extends and is named after two other attention-based models, namely Lematus, a contextual lemmatizer, and MED, a morphological (re)inflection model. Our approach does not require training separate lemmatization and tagging models, nor does it need additional resources and tools, such as morphological dictionaries or transducers. Moreover, LemMED relies solely on character-level representations and on local context. Although the model can, in principle, account for global context on sentence level, our experiments show that using just a single word of context around each target word is not only more computationally feasible, but yields better results as well. We evaluate LemMED in the framework of the SIMGMORPHON-2019 shared task on combined lemmatization and tagging. In terms of average performance LemMED ranks 5th among 13 systems and is bested only by the submissions that use contextualized embeddings.