Pith. sign in

REVIEW 1 cited by

Syntax-guided Localized Self-attention by Constituency Syntactic Distance

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 2210.11759 v1 pith:LAMJ5NMR submitted 2022-10-21 cs.CL

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

Recent works have revealed that Transformers are implicitly learning the syntactic information in its lower layers from data, albeit is highly dependent on the quality and scale of the training data. However, learning syntactic information from data is not necessary if we can leverage an external syntactic parser, which provides better parsing quality with well-defined syntactic structures. This could potentially improve Transformer's performance and sample efficiency. In this work, we propose a syntax-guided localized self-attention for Transformer that allows directly incorporating grammar structures from an external constituency parser. It prohibits the attention mechanism to overweight the grammatically distant tokens over close ones. Experimental results show that our model could consistently improve translation performance on a variety of machine translation datasets, ranging from small to large dataset sizes, and with different source languages.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Causal Graphical Models for Vision-Language Compositional Understanding

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Ordering word prediction by a dependency tree instead of left-to-right improves vision-language compositional understanding across five benchmarks.

Pith tools