CLApr 10, 2019

Simple BERT Models for Relation Extraction and Semantic Role Labeling

arXiv:1904.05255v1475 citations
Originality Synthesis-oriented
AI Analysis

This provides a strong baseline for future research in NLP tasks, though it is incremental as it applies an existing method (BERT) to specific problems.

The paper tackled relation extraction and semantic role labeling by showing that simple BERT-based models, without external features like part-of-speech tags or dependency trees, can achieve state-of-the-art performance on datasets for these tasks.

We present simple BERT-based models for relation extraction and semantic role labeling. In recent years, state-of-the-art performance has been achieved using neural models by incorporating lexical and syntactic features such as part-of-speech tags and dependency trees. In this paper, extensive experiments on datasets for these two tasks show that without using any external features, a simple BERT-based model can achieve state-of-the-art performance. To our knowledge, we are the first to successfully apply BERT in this manner. Our models provide strong baselines for future research.

Code Implementations3 repos
Foundations

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

Your Notes