A Simple Joint Model for Improved Contextual Neural Lemmatization
This work addresses lemmatization for NLP practitioners, particularly benefiting low-resource languages and those with high morphological complexity, but it is incremental as it builds on existing joint modeling approaches.
The authors tackled the NLP task of lemmatization, which maps diverse word forms to canonical lemmas, by presenting a simple joint neural model for lemmatization and morphological tagging that achieves state-of-the-art results on 20 languages from the Universal Dependencies corpora.
English verbs have multiple forms. For instance, talk may also appear as talks, talked or talking, depending on the context. The NLP task of lemmatization seeks to map these diverse forms back to a canonical one, known as the lemma. We present a simple joint neural model for lemmatization and morphological tagging that achieves state-of-the-art results on 20 languages from the Universal Dependencies corpora. Our paper describes the model in addition to training and decoding procedures. Error analysis indicates that joint morphological tagging and lemmatization is especially helpful in low-resource lemmatization and languages that display a larger degree of morphological complexity. Code and pre-trained models are available at https://sigmorphon.github.io/sharedtasks/2019/task2/.