1Cademy at Semeval-2022 Task 1: Investigating the Effectiveness of Multilingual, Multitask, and Language-Agnostic Tricks for the Reverse Dictionary Task

Zhiyong Wang, Ge Zhang, Nineli Lashkarashvili


Abstract
This paper describes our system for the Se- mEval2022 task of matching dictionary glosses to word embeddings. We focus on the Reverse Dictionary Track of the competition, which maps multilingual glosses to reconstructed vector representations. More specifically, models convert the input of sentences to three types of embeddings: SGNS, Char, and Electra. We pro- pose several experiments for applying neural network cells, general multilingual and multi-task structures, and language-agnostic tricks to the task. We also provide comparisons over different types of word embeddings and ablation studies to suggest helpful strategies. Our initial transformer-based model achieves relatively low performance. However, trials on different retokenization methodologies indicate improved performance. Our proposed Elmo- based monolingual model achieves the highest outcome, and its multitask, and multilingual varieties show competitive results as well.
Anthology ID:
2022.semeval-1.2
Volume:
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Guy Emerson, Natalie Schluter, Gabriel Stanovsky, Ritesh Kumar, Alexis Palmer, Nathan Schneider, Siddharth Singh, Shyam Ratan
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
15–22
Language:
URL:
https://aclanthology.org/2022.semeval-1.2
DOI:
10.18653/v1/2022.semeval-1.2
Bibkey:
Cite (ACL):
Zhiyong Wang, Ge Zhang, and Nineli Lashkarashvili. 2022. 1Cademy at Semeval-2022 Task 1: Investigating the Effectiveness of Multilingual, Multitask, and Language-Agnostic Tricks for the Reverse Dictionary Task. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 15–22, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
1Cademy at Semeval-2022 Task 1: Investigating the Effectiveness of Multilingual, Multitask, and Language-Agnostic Tricks for the Reverse Dictionary Task (Wang et al., SemEval 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.semeval-1.2.pdf
Video:
 https://aclanthology.org/2022.semeval-1.2.mp4