Pith. sign in

REVIEW 5 cited by

Do Attention Heads in BERT Track Syntactic Dependencies?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1911.12246 v1 pith:B2SRDAIB submitted 2019-11-27 cs.CL

Do Attention Heads in BERT Track Syntactic Dependencies?

classification cs.CL
keywords attentiondependencyheadssyntacticbertmodelsrelationssome
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We investigate the extent to which individual attention heads in pretrained transformer language models, such as BERT and RoBERTa, implicitly capture syntactic dependency relations. We employ two methods---taking the maximum attention weight and computing the maximum spanning tree---to extract implicit dependency relations from the attention weights of each layer/head, and compare them to the ground-truth Universal Dependency (UD) trees. We show that, for some UD relation types, there exist heads that can recover the dependency type significantly better than baselines on parsed English text, suggesting that some self-attention heads act as a proxy for syntactic structure. We also analyze BERT fine-tuned on two datasets---the syntax-oriented CoLA and the semantics-oriented MNLI---to investigate whether fine-tuning affects the patterns of their self-attention, but we do not observe substantial differences in the overall dependency relations extracted using our methods. Our results suggest that these models have some specialist attention heads that track individual dependency types, but no generalist head that performs holistic parsing significantly better than a trivial baseline, and that analyzing attention weights directly may not reveal much of the syntactic knowledge that BERT-style models are known to learn.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. In-context Learning and Induction Heads

    cs.LG 2022-09 unverdicted novelty 7.0

    Induction heads, which implement pattern completion in attention, develop at the same training stage as a sudden rise in in-context learning, providing evidence they are the primary mechanism for in-context learning i...

  2. Instructions Shape Production of Language, not Processing

    cs.CL 2026-05 unverdicted novelty 6.0

    Instructions trigger a production-centered mechanism in language models, with task-specific information stable in input tokens but varying strongly in output tokens and correlating with behavior.

  3. Instructions Shape Production of Language, not Processing

    cs.CL 2026-05 unverdicted novelty 5.0

    Instructions primarily shape the production stage of language models rather than the processing stage, with task-specific information and causal effects stronger in output tokens than input tokens.

  4. SSA: Improving Performance With a Better Scoring Function

    cs.CL 2025-08 unverdicted novelty 5.0

    Replacing Softmax with Scaled Signed Averaging in transformer attention improves generalization under distribution shifts for in-context learning and boosts results on NLP benchmarks.

  5. Probing Classifiers: Promises, Shortcomings, and Advances

    cs.CL 2021-02 unverdicted novelty 3.0

    Probing classifiers are a common but limited method for analyzing linguistic knowledge in neural NLP models, and this review outlines their promises, methodological shortcomings, and recent advances.