Enhancing Sequence-to-Sequence Neural Lemmatization with External Resources
This work addresses lemmatization accuracy for natural language processing tasks, offering an incremental improvement over existing methods.
The paper tackles the problem of lemmatization by enhancing a seq2seq neural model with external lemma candidates from resources like Apertium, achieving an average accuracy of 97.25% across 23 languages, which is 0.55% higher than the Stanford Stanza model.
We propose a novel hybrid approach to lemmatization that enhances the seq2seq neural model with additional lemmas extracted from an external lexicon or a rule-based system. During training, the enhanced lemmatizer learns both to generate lemmas via a sequential decoder and copy the lemma characters from the external candidates supplied during run-time. Our lemmatizer enhanced with candidates extracted from the Apertium morphological analyzer achieves statistically significant improvements compared to baseline models not utilizing additional lemma information, achieves an average accuracy of 97.25% on a set of 23 UD languages, which is 0.55% higher than obtained with the Stanford Stanza model on the same set of languages. We also compare with other methods of integrating external data into lemmatization and show that our enhanced system performs considerably better than a simple lexicon extension method based on the Stanza system, and it achieves complementary improvements w.r.t. the data augmentation method.