CLLGFeb 24, 2020

Improving BERT Fine-Tuning via Self-Ensemble and Self-Distillation

arXiv:2002.10345v178 citations
AI Analysis

This addresses the under-explored fine-tuning strategy for BERT, offering a method to enhance adaptation for NLP practitioners, though it appears incremental as it builds on existing fine-tuning approaches.

The paper tackles the problem of fine-tuning BERT for NLP tasks by proposing self-ensemble and self-distillation mechanisms, resulting in significant improvements on text classification and natural language inference tasks without external data.

Fine-tuning pre-trained language models like BERT has become an effective way in NLP and yields state-of-the-art results on many downstream tasks. Recent studies on adapting BERT to new tasks mainly focus on modifying the model structure, re-designing the pre-train tasks, and leveraging external data and knowledge. The fine-tuning strategy itself has yet to be fully explored. In this paper, we improve the fine-tuning of BERT with two effective mechanisms: self-ensemble and self-distillation. The experiments on text classification and natural language inference tasks show our proposed methods can significantly improve the adaption of BERT without any external data or knowledge.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes