RIGA at SemEval-2022 Task 1: Scaling Recurrent Neural Networks for CODWOE Dictionary Modeling

Eduards Mukans, Gus Strazds, Guntis Barzdins


Abstract
Described are our two entries “emukans” and “guntis” for the definition modeling track of CODWOE SemEval-2022 Task 1. Our approach is based on careful scaling of a GRU recurrent neural network, which exhibits double descent of errors, corresponding to significant improvements also per human judgement. Our results are in the middle of the ranking table per official automatic metrics.
Anthology ID:
2022.semeval-1.9
Volume:
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
82–87
Language:
URL:
https://aclanthology.org/2022.semeval-1.9
DOI:
10.18653/v1/2022.semeval-1.9
Bibkey:
Cite (ACL):
Eduards Mukans, Gus Strazds, and Guntis Barzdins. 2022. RIGA at SemEval-2022 Task 1: Scaling Recurrent Neural Networks for CODWOE Dictionary Modeling. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 82–87, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
RIGA at SemEval-2022 Task 1: Scaling Recurrent Neural Networks for CODWOE Dictionary Modeling (Mukans et al., SemEval 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2022.semeval-1.9.pdf
Video:
 https://preview.aclanthology.org/emnlp-22-attachments/2022.semeval-1.9.mp4