Skip to content
conftrace_
2023 SemEval SemEval 2023

Francis Bacon at SemEval-2023 Task 4: Ensembling BERT and GloVe for Value Identification in Arguments

Abstract

AbstractIn 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.

Authors

Kenan Hasanaliyev, Kevin Li, Saanvi Chawla, Michael Nath, Rohan Sanda, Justin Wu, William Huang, Daniel Yang, Shane Mion, Kiran Bhat

Topics

Machine Learning > Core Methods > Classification Machine Learning > Optimization & Theory > Optimization Deep Learning > Architectures > Transformers

Keywords

ensemble learning text classification ridge regression word embedding transformer model
Download PDF

More from SemEval 2023

All SemEval 2023 papers →
DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition
ROZAM at SemEval 2023 Task 9: Multilingual Tweet Intimacy Analysis
Prodicus at SemEval-2023 Task 4: Enhancing Human Value Detection with Data Augmentation and Fine-Tuned Language Models
UAlberta at SemEval-2023 Task 1: Context Augmentation and Translation for Multilingual Visual Word Sense Disambiguation
iREL at SemEval-2023 Task 9: Improving understanding of multilingual Tweets using Translation-Based Augmentation and Domain Adapted Pre-Trained Models
Team TheSyllogist at SemEval-2023 Task 3: Language-Agnostic Framing Detection in Multi-Lingual Online News: A Zero-Shot Transfer Approach