We present a simple joint neural model for lemmatization and morpho-logical tagging that achieves state-of-the-art results on 20 languages from the Universal Dependencies corpora. …

We propose an alternative for this, in form of a tool that performs lemmati-zation in the space of word embeddings.

Multi-Task Learning for Sequence-to-Sequence Neural Models of Lemmatization. Lauren Watson. Master of Science Artificial Intelligence School of Informatics University of Edinburgh 2018. 3. …

Lemmatization is the process of grouping inflected forms together as a single base form. Lemmatize a vector of strings. lemmatize_strings(x, dictionary = lexicon::hash_lemmas, ...) …

In this paper, we critically evaluate the widespread assumption that deep learning NLP models do not require lemmatized input. To test this, we trained versions of contextualised word …

We present a simple joint neu-ral model for lemmatization and morphological tagging that achieves state-of-the-art results on 20 languages from the Universal Dependen-cies corpora. …

In this study we establish the first measurements of the effect of token-based lemmatization on topic models on a corpus of morphologically rich language. Syntactic information is not …