Lemmatization of Nouns in the Azerbaijani Language using Embeddings

This paper introduces an innovative method for noun lemmatization in the Azerbaijani language, leveraging word vector representations to enhance lemma candidate selection. By employing the Word2Vec model to train vector representations and utilizing cosine similarity for lemma identification, the method shows notable improvements over traditional approaches. The effectiveness of this technique is validated through experimental evidence, marking a significant contribution to Azerbaijani language processing advancements.