| Abstract |
The paper reports a pilot study on the detection of lexical semantic variation in modern Swedish. The starting point of the study is the meaning descriptions of around 65,000 headwords in ’The Contemporary Dictionary of the Swedish Academy’ (SO, 2021) covering approximately 100,000 different senses. In our work, we aim to explore the potential of the latest computational methods to discover outdated definitions in SO and update them. For this, we make use of the DURel tool (Schlechtweg et al., 2018, 2024) which relies on state of-the-art language models for the automatic semantic analysis of word usages. The work resulted in drawing lexicographers’ attention to both main senses and subsenses that should be added to the dictionary. It has also demonstrated that certain meaning descriptions in SO are too general and should be split in accordance with the current principles for the semantic descriptions in the dictionary. |
| BibTex |
@inproceedings{euralex_2024_paper_13,
address = {Cavtat},
title = {Revealing Semantic Variation in Swedish Using Computational Models of Semantic Proximity – Results From Lexicographical Experiments},isbn = {978-953-7967-77-2},
shorttitle = {Euralex 2024},
url = {},
language = {eng},
booktitle = {Lexicography and Semantics. Proceedings of the XXI EURALEX International Congress},
publisher = {Institut za hrvatski jezik},
author = {Sköldberg, Emma and Virk, Shafqat Mumtaz and Sander, Pauline and Hengchen, Simon and Schlechtweg, Dominik},
editor = {Despot, Kristina Š. and Ostroški Anić, Ana and Brač, Ivana},
year = {2024},
pages = {169-183}
} |
