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

TL;DR

This paper explores multilingual, multitask, and language-agnostic techniques for the reverse dictionary task, comparing various models and strategies, with the proposed Elmo-based monolingual model achieving the best results.

Contribution

It introduces novel multilingual, multitask, and language-agnostic approaches for reverse dictionary mapping, demonstrating their effectiveness through extensive experiments and ablation studies.

Findings

Elmo-based monolingual model outperforms other models

Multitask and multilingual variants show competitive results

Retokenization improves model performance

Abstract

This paper describes our system for the SemEval2022 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 propose several experiments for applying neural network cells, general multilingual and multitask 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 Elmobased monolingual model achieves the highest outcome, and its multitask, and multilingual varieties show competitive results as well.