OPD@NL4Opt: An ensemble approach for the NER task of the optimization problem
This work addresses a domain-specific problem in optimization, but it is incremental as it applies existing methods like fine-tuning and ensembling to a competition dataset.
The paper tackled the named entity recognition (NER) task in the NL4Opt competition by developing an ensemble approach, achieving a micro-averaged F1 score of 93.3% and securing second prize.
In this paper, we present an ensemble approach for the NL4Opt competition subtask 1(NER task). For this task, we first fine tune the pretrained language models based on the competition dataset. Then we adopt differential learning rates and adversarial training strategies to enhance the model generalization and robustness. Additionally, we use a model ensemble method for the final prediction, which achieves a micro-averaged F1 score of 93.3% and attains the second prize in the NER task.