Discovery Team at SemEval-2020 Task 1: Context-sensitive Embeddings Not Always Better than Static for Semantic Change Detection

Show full item record



Permalink

http://hdl.handle.net/10138/324849

Citation

Martinc , M , Montariol , S , Zosa , E & Pivovarova , L 2020 , Discovery Team at SemEval-2020 Task 1: Context-sensitive Embeddings Not Always Better than Static for Semantic Change Detection . in Proceedings of the Fourteenth Workshop on Semantic Evaluation . International Committee for Computational Linguistics , Barcelona , pp. 67-73 , International Workshop on Semantic Evaluation , Barcelona , Spain , 12/12/2020 . < https://www.aclweb.org/anthology/2020.semeval-1.6 >

Title: Discovery Team at SemEval-2020 Task 1: Context-sensitive Embeddings Not Always Better than Static for Semantic Change Detection
Author: Martinc, Matej; Montariol, Syrielle; Zosa, Elaine; Pivovarova, Lidia
Contributor: University of Helsinki, Department of Computer Science
University of Helsinki, Discovery Research Group/Prof. Hannu Toivonen
Publisher: International Committee for Computational Linguistics
Date: 2020-12
Language: eng
Belongs to series: Proceedings of the Fourteenth Workshop on Semantic Evaluation
ISBN: 978-1-952148-31-6
URI: http://hdl.handle.net/10138/324849
Abstract: This paper describes the approaches used by the Discovery Team to solve SemEval-2020 Task 1 - Unsupervised Lexical Semantic Change Detection. The proposed method is based on clustering of BERT contextual embeddings, followed by a comparison of cluster distributions across time. The best results were obtained by an ensemble of this method and static Word2Vec embeddings. According to the official results, our approach proved the best for Latin in Subtask 2.
Subject: 113 Computer and information sciences
Rights:


Files in this item

Total number of downloads: Loading...

Files Size Format View
2020.semeval_1.6.pdf 237.4Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record