Simple BERT Models for Relation Extraction and Semantic Role Labeling

Peng Shi, Jimmy Lin
4/10/2019
cs.CL

Official code: Impavidity/relogic (29 stars, MIT, last commit 2022-12-16).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

Impavidity/relogicOfficial100%
MIT

hopefully I can continuously develop the project.

296Shell, PythonJul 16, 20193 years agoMIT

Similar Papers

A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling

88% match1 repo1912017

Joint entity recognition and relation extraction as a multi-head selection problem

85% match1 repo4142018

Entity or Relation Embeddings? An Analysis of Encoding Strategies for Relation Extraction

84% match1 repo32023

Generalizing Natural Language Analysis through Span-relation Representations

84% match1 repo912019

NERO: A Neural Rule Grounding Framework for Label-Efficient Relation Extraction

83% match1 repo462019

Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

83% match1 repo1912017

Cite this paper

@article{shi2019simple,
  title  = {Simple BERT Models for Relation Extraction and Semantic Role Labeling},
  author = {Peng Shi and Jimmy Lin},
  year   = {2019},
  eprint = {1904.05255},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1904.05255}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1904.05255.svg)](https://codeofpaper.com/paper/1904.05255)

Discussion