JSI at SemEval-2022 Task 1: CODWOE - Reverse Dictionary: Monolingual and cross-lingual approaches

Thi Hong Hanh Tran, Matej Martinc, Matthew Purver, Senja Pollak


Abstract
The reverse dictionary task is a sequence-to-vector task in which a gloss is provided as input, and the output must be 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 effect of a Transformer-based model with cross-lingual zero-shot learning to improve the reverse dictionary performance. Our experiments are conducted in five languages in the CODWOE dataset, including English, French, Italian, Spanish, and Russian. Even if we did not achieve a good ranking in the CODWOE competition, we show that our work partially improves the current baseline from the organizers with a hypothesis on the impact of LSTM in monolingual, multilingual, and zero-shot learning. All the codes are available at https://github.com/honghanhh/codwoe2021.
Anthology ID:
2022.semeval-1.12
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:
101–106
Language:
URL:
https://aclanthology.org/2022.semeval-1.12
DOI:
10.18653/v1/2022.semeval-1.12
Bibkey:
Cite (ACL):
Thi Hong Hanh Tran, Matej Martinc, Matthew Purver, and Senja Pollak. 2022. JSI at SemEval-2022 Task 1: CODWOE - Reverse Dictionary: Monolingual and cross-lingual approaches. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 101–106, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
JSI at SemEval-2022 Task 1: CODWOE - Reverse Dictionary: Monolingual and cross-lingual approaches (Tran et al., SemEval 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2022.semeval-1.12.pdf
Video:
 https://preview.aclanthology.org/naacl24-info/2022.semeval-1.12.mp4
Code
 honghanhh/codwoe2021