Lexical semantic change detection is a new and innovative research field. The optimal fine-tuning of models including pre- and post-processing is largely unclear. We optimize existing models by (i) pre-training on large corpora and refining on diachronic target corpora tackling the notorious small data problem, and (ii) applying post-processing transformations that have been shown to improve performance on synchronic tasks. Our results provide a guide for the application and optimization of lexical semantic change detection models across various learning scenarios.
%0 Conference Paper
%1 kaiser-etal-2021-effects
%A Kaiser, Jens
%A Kurtyigit, Sinan
%A Kotchourko, Serge
%A Schlechtweg, Dominik
%B Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%C Online
%D 2021
%I Association for Computational Linguistics
%K myown
%P 125--137
%R 10.18653/v1/2021.eacl-main.10
%T Effects of Pre- and Post-Processing on type-based Embeddings in Lexical Semantic Change Detection
%U https://aclanthology.org/2021.eacl-main.10
%X Lexical semantic change detection is a new and innovative research field. The optimal fine-tuning of models including pre- and post-processing is largely unclear. We optimize existing models by (i) pre-training on large corpora and refining on diachronic target corpora tackling the notorious small data problem, and (ii) applying post-processing transformations that have been shown to improve performance on synchronic tasks. Our results provide a guide for the application and optimization of lexical semantic change detection models across various learning scenarios.
@inproceedings{kaiser-etal-2021-effects,
abstract = {Lexical semantic change detection is a new and innovative research field. The optimal fine-tuning of models including pre- and post-processing is largely unclear. We optimize existing models by (i) pre-training on large corpora and refining on diachronic target corpora tackling the notorious small data problem, and (ii) applying post-processing transformations that have been shown to improve performance on synchronic tasks. Our results provide a guide for the application and optimization of lexical semantic change detection models across various learning scenarios.},
added-at = {2022-10-11T18:37:05.000+0200},
address = {Online},
author = {Kaiser, Jens and Kurtyigit, Sinan and Kotchourko, Serge and Schlechtweg, Dominik},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2373677bd705e71f035c0babda6c666c0/dschlechtweg},
booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume},
doi = {10.18653/v1/2021.eacl-main.10},
interhash = {58758a6b1b8998d06dc0099059f61577},
intrahash = {373677bd705e71f035c0babda6c666c0},
keywords = {myown},
month = apr,
pages = {125--137},
publisher = {Association for Computational Linguistics},
timestamp = {2022-10-11T16:37:05.000+0200},
title = {Effects of Pre- and Post-Processing on type-based Embeddings in Lexical Semantic Change Detection},
url = {https://aclanthology.org/2021.eacl-main.10},
year = 2021
}