Discriminating between lexico-semantic relations with the specialization tensor model
NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
MetadataShow full item record
Glavaš, G., & Vulić, I. (2018). Discriminating between lexico-semantic relations with the specialization tensor model. NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, 2 181-187. https://doi.org/10.17863/CAM.26774
We present a simple and effective feed-forward neural architecture for discriminating between lexico-semantic relations (synonymy, antonymy, hypernymy, and meronymy). Our Specialization Tensor Model (STM) simultaneously produces multiple different specializations of input distributional word vectors, tailored for predicting lexico-semantic relations for word pairs. STM outperforms more complex state-of-the-art architectures on two benchmark datasets and exhibits stable performance across languages. We also show that, if coupled with a lingual distributional space, the proposed model can transfer the prediction of lexico-semantic relations to a resource-lean target language without any training data.
ECH2020 EUROPEAN RESEARCH COUNCIL (ERC) (648909)
This record's DOI: https://doi.org/10.17863/CAM.26774
This record's URL: https://www.repository.cam.ac.uk/handle/1810/279399