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

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

7 Mar 2021EACL 2021 2arXiv:2103.04350archive 2025-07-28

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

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

nkh2235/SyntaxBERT officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Natural Language Understanding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdafactorAdamAttentionAttention DropoutBERTBPEDense ConnectionsDropoutGated Linear UnitInverse Square Root ScheduleLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionRoBERTaSentencePieceSoftmaxT5TransformerWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections