LemMED: Fast and Effective Neural Morphological Analysis with Short Context Windows
This work addresses efficient morphological analysis for natural language processing, but it is incremental as it builds on existing attention-based models.
The authors tackled the problem of contextual morphological analysis (combined lemmatization and tagging) by introducing LemMED, a character-level encoder-decoder model that uses only local context, achieving 5th place out of 13 systems in the SIGMORPHON-2019 shared task.
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.