Sidansvarig: Webbredaktion
Sidan uppdaterades: 2012-09-11 15:12
Författare |
Haim Dubossarsky Simon Hengchen Nina Tahmasebi Dominik Schlechtweg |
---|---|
Publicerad i | Computational linguistics - Association for Computational Linguistics |
ISSN | 0891-2017 |
Publiceringsår | 2019 |
Publicerad vid |
Institutionen för litteratur, idéhistoria och religion Institutionen för svenska språket |
Språk | en |
Länkar |
https://arxiv.org/abs/1906.01688 |
Ämnesord | Lexical semantic change, evaluation, data science |
Ämneskategorier | Språkteknologi (språkvetenskaplig databehandling), Informationsteknik |
State-of-the-art models of lexical semantic change detection suffer from noise stemming from vector space alignment. We have empirically tested the Temporal Referencing method for lexical semantic change and show that, by avoiding alignment, it is less affected by this noise. We show that, trained on a diachronic corpus, the skip-gram with negative sampling architecture with temporal referencing outperforms alignment models on a synthetic task as well as a manual testset. We introduce a principled way to simulate lexical semantic change and systematically control for possible biases.