Methods › Sequential › Temporal Convolutions › Span-Based Dynamic Convolution
Span-Based Dynamic Convolution
Introduced by Zi-Hang Jiang et al. in ConvBERT: Improving BERT with Span-based Dynamic Convolution
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Span-Based Dynamic Convolution is a type of convolution used in the ConvBERT architecture to capture local dependencies between tokens. Kernels are generated by taking in a local span of current token, which better utilizes local dependency and discriminates different meanings of the same token (e.g., if “a” is in front of “can” in the input sentence, “can” is apparently a noun not a verb).
Specifically, with classic convolution, we would have fixed parameters shared for all input tokens. Dynamic convolution is therefore preferable because it has higher flexibility in capturing local dependencies of different tokens. Dynamic convolution uses a kernel generator to produce different kernels for different input tokens. However, such dynamic convolution cannot differentiate the same tokens within different context and generate the same kernels (e.g., the three “can” in Figure (b)).
Therefore the span-based dynamic convolution is developed to produce more adaptive convolution kernels by receiving an input span instead of only a single token, which enables discrimination of generated kernels for the same tokens within different context. For example, as shown in Figure (c), span-based dynamic convolution produces different kernels for different “can” tokens.
Papers archive 2025-07-28
6 shown of 6, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Beyond Simple Concatenation: Fairly Assessing PLM Architectures for Multi-Chain Protein-Protein Interactions Prediction 26 May 2025 · 0 repositories · arXiv:2505.20036
-
Navigating Nuance: In Quest for Political Truth 1 Jan 2025 · 1 repository · arXiv:2501.00782
-
ChatGPT v.s. Media Bias: A Comparative Study of GPT-3.5 and Fine-tuned Language Models 29 Mar 2024 · 0 repositories · arXiv:2403.20158
-
M³Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection 15 Sep 2023 · 1 repository · arXiv:2309.08365
-
Transformer Based Punctuation Restoration for Turkish 15 Sep 2023 · 1 repository
-
ConvBERT: Improving BERT with Span-based Dynamic Convolution 6 Aug 2020 · 8 repositories · arXiv:2008.02496
Tasks archive 2025-07-28
16 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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