DCC-Uchile at SemEval-2020 Task 1: Temporal Referencing Word Embeddings

Frank D. Zamora-Reina, Felipe Bravo-Marquez


Abstract
We present a system for the task of unsupervised lexical change detection: given a target word and two corpora spanning different periods of time, automatically detects whether the word has lost or gained senses from one corpus to another. Our system employs the temporal referencing method to obtain compatible representations of target words in different periods of time. This is done by concatenating corpora of different periods and performing a temporal referencing of target words i.e., treating occurrences of target words in different periods as two independent tokens. Afterwards, we train word embeddings on the joint corpus and compare the referenced vectors of each target word using cosine similarity. Our submission was ranked 7th among 34 teams for subtask 1, obtaining an average accuracy of 0.637, only 0.050 points behind the first ranked system.
Anthology ID:
2020.semeval-1.23
Volume:
Proceedings of the Fourteenth Workshop on Semantic Evaluation
Month:
December
Year:
2020
Address:
Barcelona (online)
Editors:
Aurelie Herbelot, Xiaodan Zhu, Alexis Palmer, Nathan Schneider, Jonathan May, Ekaterina Shutova
Venue:
SemEval
SIG:
SIGLEX
Publisher:
International Committee for Computational Linguistics
Note:
Pages:
194–200
Language:
URL:
https://aclanthology.org/2020.semeval-1.23
DOI:
10.18653/v1/2020.semeval-1.23
Bibkey:
Cite (ACL):
Frank D. Zamora-Reina and Felipe Bravo-Marquez. 2020. DCC-Uchile at SemEval-2020 Task 1: Temporal Referencing Word Embeddings. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 194–200, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
DCC-Uchile at SemEval-2020 Task 1: Temporal Referencing Word Embeddings (Zamora-Reina & Bravo-Marquez, SemEval 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.semeval-1.23.pdf