BERT Model
BERT, a powerful transformer-based language model, is primarily used for natural language processing tasks by leveraging contextualized word embeddings to understand the meaning of text. Current research focuses on improving BERT's efficiency (e.g., through pruning and distillation), adapting it to specific domains (e.g., finance, medicine, law), and exploring its application in diverse areas such as text classification, information extraction, and data imputation. This versatility makes BERT a significant tool for advancing NLP research and impacting various applications, from improving healthcare diagnostics to enhancing search engine capabilities.
Papers
Improving Zero-Shot Text Matching for Financial Auditing with Large Language Models
Lars Hillebrand, Armin Berger, Tobias Deußer, Tim Dilmaghani, Mohamed Khaled, Bernd Kliem, Rüdiger Loitz, Maren Pielka, David Leonhard, Christian Bauckhage, Rafet Sifa
Enhancing Phenotype Recognition in Clinical Notes Using Large Language Models: PhenoBCBERT and PhenoGPT
Jingye Yang, Cong Liu, Wendy Deng, Da Wu, Chunhua Weng, Yunyun Zhou, Kai Wang
Sensi-BERT: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient BERT
Souvik Kundu, Sharath Nittur Sridhar, Maciej Szankin, Sairam Sundaresan
Towards spoken dialect identification of Irish
Liam Lonergan, Mengjie Qian, Neasa Ní Chiaráin, Christer Gobl, Ailbhe Ní Chasaide
Improving BERT with Hybrid Pooling Network and Drop Mask
Qian Chen, Wen Wang, Qinglin Zhang, Chong Deng, Ma Yukun, Siqi Zheng