Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change

Haim Dubossarsky, Simon Hengchen, Nina Tahmasebi, Dominik Schlechtweg


Abstract
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.
Anthology ID:
P19-1044
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
457–470
Language:
URL:
https://aclanthology.org/P19-1044
DOI:
10.18653/v1/P19-1044
Bibkey:
Cite (ACL):
Haim Dubossarsky, Simon Hengchen, Nina Tahmasebi, and Dominik Schlechtweg. 2019. Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 457–470, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change (Dubossarsky et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1044.pdf
Code
 Garrafao/TemporalReferencing