Analysing the semantic content of static Hungarian embedding spaces

@InProceedings{ficsor2021mszny,
    author="Ficsor, Tam{\'a}s and Berend, G{\'a}bor",
    booktitle = {XVII. Magyar Sz{\'a}m{\'i}t{\'o}g{\'e}pes Nyelv{\'e}szeti Konferencia},
    title = {Analysing the semantic content of static Hungarian embedding spaces},
    address = {Szeged},
    publisher = {Szegedi Tudom{\'a}nyegyetem, Informatikai Int{\'e}zet},
    year={2021},
    pages={91--105},
    abstract="Word embeddings can encode semantic features and have achieved many recent successes in solving NLP tasks. Although word embeddings have high success on several downstream tasks, there is no trivial approach to extract lexical information from them. We propose a transformation that amplifies desired semantic features in the basis of the embedding space. We generate these semantic features by a distant supervised approach, to make them applicable for Hungarian embedding spaces. We propose the Hellinger distance in order to perform a transformation to an interpretable embedding space. Furthermore, we extend our research to sparse word representations as well, since sparse representations are considered to be highly interpretable.",
    isbn="978-9-633-06781-9"
}