PyTorch Implementation of "Monotonic Chunkwise Attention" (ICLR 2018)
-
Updated
Apr 2, 2018 - Python
#
hard-attention
Here are 8 public repositories matching this topic...
Repository for Attention Algorithm
-
Updated
Mar 30, 2018 - Jupyter Notebook
Feature Selection Gates with Gradient Routing
regression feature-selection image-classification attention gradient-descent attention-mechanism gradient-boosting hard-attention vision-transformers
-
Updated
May 10, 2025 - Python
Transliteration using Sequence to Sequence transduction using Hard Monotonic Attention, based on our EMNLP 2018 paper
-
Updated
Feb 13, 2019 - Python
45k context transformer for splice site prediction implemented with PyTorch.
rna-seq pytorch transformer hard-attention splice-junctions transformer-models splice-site splice-variants splice-site-prediction
-
Updated
Jul 24, 2025 - Jupyter Notebook
Recurrent Visual Attention using PyTorch; Catch and MNIST classification
-
Updated
Feb 23, 2022 - Python
End-to-end trainable autoregressive and non-autoregressive transducers using hard attention
-
Updated
Jan 14, 2023 - Python
📝 Streamline text processing in Arabic and English with ChunkWise, a library offering 31 chunking strategies for NLP and RAG systems.
r csv database utilities dplyr pytorch chunk data-analysis seq2seq mapreduce aggregation data-processing attention-mechanism data-science-toolbox chunkwise-processing hard-attention monotonic-attention
-
Updated
Jan 5, 2026 - Python
Improve this page
Add a description, image, and links to the hard-attention topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the hard-attention topic, visit your repo's landing page and select "manage topics."