Repozytorium publikacji - Politechnika Gdańska

This study introduces a method for the improvement of word vectors, addressing the limitations of traditional approaches like Word2Vec or GloVe through introducing into embeddings richer semantic properties. Our approach leverages supervised learning methods, with shifts in vectors in the representation space enhancing the quality of word embeddings. This ensures better alignment with semantic reference resources, such as WordNet. The effectiveness of the method has been demonstrated through the application of modified embeddings to text classification and clustering. We also show how our method influences document class distributions, visualized through PCA projections. By comparing our results with state-of-the-art approaches and achieving better accuracy, we confirm the effectiveness of the proposed method. The results underscore the potential of adaptive embeddings to improve both the accuracy and efficiency of semantic analysis across a range of NLP.

Autorzy

• dr hab. inż. Julian Szymański link otwiera się w nowej karcie ,
• Maksymilian Operlejn link otwiera się w nowej karcie ,
• dr Paweł Weichbroth link otwiera się w nowej karcie