Discovery Team at SemEval-2020 Task 1: Context-sensitive Embeddings Not Always Better than Static for Semantic Change Detection
Permalänk
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 >
| Titel: | Discovery Team at SemEval-2020 Task 1: Context-sensitive Embeddings Not Always Better than Static for Semantic Change Detection |
| Författare: | Martinc, Matej; Montariol, Syrielle; Zosa, Elaine; Pivovarova, Lidia |
| Upphovmannens organisation: | Department of Computer Science Discovery Research Group/Prof. Hannu Toivonen |
| Utgivare: | International Committee for Computational Linguistics |
| Datum: | 2020-12 |
| Språk: | eng |
| Tillhör serie: | Proceedings of the Fourteenth Workshop on Semantic Evaluation |
| ISBN: | 978-1-952148-31-6 |
| Permanenta länken (URI): | http://hdl.handle.net/10138/324849 |
| Abstrakt: | 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 |
| Referentgranskad: | Ja |
| Licens: | cc_by_nc_sa |
| Användningsbegränsning: | openAccess |
| Parallelpublicerad version: | publishedVersion |
Filer under denna titel
Totalt antal nerladdningar: Laddar...
| Filer | Storlek | Format | Granska |
|---|---|---|---|
| 2020.semeval_1.6.pdf | 237.4Kb | Granska/Öppna |
Detta dokument registreras i samling:
-
TUHAT-artikkelit [50505]