Using Deep Mixture-of-Experts to Detect Word Meaning Shift for TempoWiC
This is an incremental improvement for a specific NLP benchmark task (TempoWiC).
The paper tackles the TempoWiC task of detecting word meaning shift, achieving first place with a macro-F1 score of 77.05% by using data cleaning, augmentation, adversarial training, and a Mixture-of-Experts approach that integrates POS and semantic features.
This paper mainly describes the dma submission to the TempoWiC task, which achieves a macro-F1 score of 77.05% and attains the first place in this task. We first explore the impact of different pre-trained language models. Then we adopt data cleaning, data augmentation, and adversarial training strategies to enhance the model generalization and robustness. For further improvement, we integrate POS information and word semantic representation using a Mixture-of-Experts (MoE) approach. The experimental results show that MoE can overcome the feature overuse issue and combine the context, POS, and word semantic features well. Additionally, we use a model ensemble method for the final prediction, which has been proven effective by many research works.