CoChat

What do they capture?: a structural analysis of pre-trained language models for source code

Wan, Yao, Zhao, Wei, Zhang, Hongyu, Sui, Yulei, Xu, Guandong, Jin, Hai · 2022 · Proceedings of the 44th International Conference on Software Engineering
Cited by 73

The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.

Abstract

Recently, many pre-trained language models for source code have been proposed to model the context of code and serve as a basis for downstream code intelligence tasks such as code completion, code search, and code summarization. These models leverage masked pre-training and Transformer and have achieved promising results. However, currently there is still little progress regarding interpretability of existing pre-trained code models. It is not clear why these models work and what feature correlations they can capture. In this paper, we conduct a thorough structural analysis aiming to provide an interpretation of pre-trained language models for source code (e.g., CodeBERT, and GraphCodeBERT) from three distinctive perspectives: (1) attention analysis, (2) probing on the word embedding, and (3) syntax tree induction. Through comprehensive analysis, this paper reveals several insightful findings that may inspire future studies: (1) Attention aligns strongly with the syntax structure of code. (2) Pre-training language models of code can preserve the syntax structure of code in the intermediate representations of each Transformer layer. (3) The pre-trained models of code have the ability of inducing syntax trees of code. Theses findings suggest that it may be helpful to incorporate the syntax structure of code into the process of pre-training for better code representations.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3510003.3510050

Cites

11 of 11 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 11 references

Cited by

See all 73

Metadata

Authors
Wan, Y., Zhao, W., Zhang, H., Sui, Y., Xu, G., & Jin, H.
Venue
Proceedings of the 44th International Conference on Software Engineering
Publisher
ACM
Published
2022-05-21
Pages
2377-2388
ISSN
0270-5257 (ISSN-L)
OpenAlex
W4284710241
Cited by
73
References
11
FWCI
14.66
Type
conference paper
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: What do they capture?: a structural analysis of pre-trained language models for source code. https://app.cochat.ai/papers/10.1145/3510003.3510050
The paper
Wan, Y., Zhao, W., Zhang, H., Sui, Y., Xu, G., & Jin, H. (2022). What do they capture?: a structural analysis of pre-trained language models for source code. Proceedings of the 44th International Conference on Software Engineering. https://doi.org/10.1145/3510003.3510050

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.