MLLabs-LIG at TempoWiC 2022: A Generative Approach for Examining Temporal Meaning Shift

Chenyang Lyu, Yongxin Zhou, Tianbo Ji


Abstract
In this paper, we present our system for the EvoNLP 2022 shared task Temporal Meaning Shift (TempoWiC). Different from the typically used discriminative model, we propose a generative approach based on pre-trained generation models. The basic architecture of our system is a seq2seq model where the input sequence consists of two documents followed by a question asking whether the meaning of target word changed or not, the target output sequence is a declarative sentence describing the meaning of target word changed or not. The experimental results on TempoWiC test set show that our best system (with time information) obtained an accuracy and Marco F-1 score of 68.09% and 62.59% respectively, which ranked 12th among all submitted systems. The results have shown the plausibility of using generation model for WiC tasks, meanwhile also indicate there’s still room for further improvement.
Anthology ID:
2022.evonlp-1.1
Volume:
Proceedings of the First Workshop on Ever Evolving NLP (EvoNLP)
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Francesco Barbieri, Jose Camacho-Collados, Bhuwan Dhingra, Luis Espinosa-Anke, Elena Gribovskaya, Angeliki Lazaridou, Daniel Loureiro, Leonardo Neves
Venue:
EvoNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–6
Language:
URL:
https://aclanthology.org/2022.evonlp-1.1
DOI:
10.18653/v1/2022.evonlp-1.1
Bibkey:
Cite (ACL):
Chenyang Lyu, Yongxin Zhou, and Tianbo Ji. 2022. MLLabs-LIG at TempoWiC 2022: A Generative Approach for Examining Temporal Meaning Shift. In Proceedings of the First Workshop on Ever Evolving NLP (EvoNLP), pages 1–6, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
MLLabs-LIG at TempoWiC 2022: A Generative Approach for Examining Temporal Meaning Shift (Lyu et al., EvoNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.evonlp-1.1.pdf