JSI at SemEval-2022 Task 1: CODWOE - Reverse Dictionary: Monolingual and cross-lingual approaches
Thi Hong Hanh Tran, Matej Martinc, Matthew Purver, Senja Pollak · Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022) · 2022
The reverse dictionary is a sequence-to-vector task in which a gloss is provided as input, and the model is trained to output a semantically matching word vector.The reverse dictionary is useful in practical applications such as solving the tip-of-the-tongue problem, helping new language learners, etc.In this paper, we evaluate the Transformer-based model with the added LSTM layer for the task at hand in a monolingual, multilingual, and cross-lingual zero-shot setting.Experiments are conducted in five languages in the COD-WOE dataset, namely English, French, Italian, Spanish, and Russian.Our work partially improves the current baseline of the CODWOE competition and offers insight into the feasibility of the cross-lingual methodology for the reverse dictionary task.The code is available at https://github.com/honghanhh/codwoe2021.