Francis Bacon at SemEval-2023 Task 4: Ensembling BERT and GloVe for Value Identification in Arguments
Kenan Hasanaliyev, Kevin Li, Saanvi Chawla, Michael Nath, Rohan Sanda, Justin Wu, William Huang, Daniel Yang, Shane Mion, Kiran Bhat
The 17th International Workshop on Semantic Evaluation (SemEval-2023) Task 4: valueeval: identification of human values behind arguments Paper
TLDR:
In this paper, we discuss our efforts on SemEval-2023 Task4, a task to classify the human value categoriesthat an argument draws on. Arguments consist of a premise, conclusion,and the premise's stance on the conclusion. Our team experimented with GloVe embeddings and fine-tuning BERT. We found that
You can open the
#paper-SemEval_307
channel in a separate window.
Abstract:
In this paper, we discuss our efforts on SemEval-2023 Task4, a task to classify the human value categoriesthat an argument draws on. Arguments consist of a premise, conclusion,and the premise's stance on the conclusion. Our team experimented with GloVe embeddings and fine-tuning BERT. We found that an ensembling of BERT and GloVe with RidgeRegression worked the best.