Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

preprint · Greater South Information System · 2021

Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees

Jiangang Bai, Yujing Wang, Yiren Chen, Yaming Yang, Jing Bai, Jing Yu, Yunhai Tong

Cited by 18Open access

Abstract

Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information.Meanwhile, syntactic information has been proved to be crucial for the success of NLP applications.However, how to incorporate the syntax trees effectively and efficiently into pre-trained Transformers is still unsettled.In this paper, we address this problem by proposing a novel framework named Syntax-BERT.This framework works in a plug-and-play mode and is applicable to an arbitrary pre-trained checkpoint based on Transformer architecture.Experiments on various datasets of natural language understanding verify the effectiveness of syntax trees and achieve consistent improvement over multiple pre-trained models, including BERT, RoBERTa, and T5.

Cite this paper

APA 7

Bai, J., Wang, Y., Chen, Y., Yang, Y., Bai, J., Yu, J., & Tong, Y. (2021). Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees. Greater South Information System. https://doi.org/10.60692/3pex6-s8r96

MLA 9

Bai, Jiangang, et al. “Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees.” Greater South Information System, 2021, https://doi.org/10.60692/3pex6-s8r96.

Chicago

Bai, Jiangang, Yujing Wang, Yiren Chen, Yaming Yang, Jing Bai, Jing Yu, and Yunhai Tong. 2021. “Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees.” Greater South Information System. https://doi.org/10.60692/3pex6-s8r96.

Harvard

Bai, J. et al. (2021) ‘Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees’, Greater South Information System. Available at: https://doi.org/10.60692/3pex6-s8r96.

BibTeX
@misc{bai2021syntax,
  title = {{Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees}},
  author = {Bai, Jiangang and Wang, Yujing and Chen, Yiren and Yang, Yaming and Bai, Jing and Yu, Jing and Tong, Yunhai},
  journal = {Greater South Information System},
  year = {2021},
  doi = {10.60692/3pex6-s8r96}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.

Related papers