Hierarchical Attention Transformer (HAT) / hierarchical-transformer-base-4096-v2

Disclaimer 🚧 ⚠️

This is an experimental version of HAT, trying to make HAT a native part of Transformers library. Please use ONLY kiddothe2b/hierarchical-transformer-base-4096 for the moment.

Model description

This is a Hierarchical Attention Transformer (HAT) model as presented in An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification (Chalkidis et al., 2022).

The model has been warm-started re-using the weights of RoBERTa (Liu et al., 2019), and continued pre-trained for MLM in long sequences following the paradigm of Longformer released by Beltagy et al. (2020). It supports sequences of length up to 4,096.

HAT uses hierarchical attention, which is a combination of segment-wise and cross-segment attention operations. You can think of segments as paragraphs or sentences.

Citing

If you use HAT in your research, please cite:

An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification. Ilias Chalkidis, Xiang Dai, Manos Fergadiotis, Prodromos Malakasiotis, and Desmond Elliott. 2022. arXiv:2210.05529 (Preprint).

@misc{chalkidis-etal-2022-hat,
  url = {https://arxiv.org/abs/2210.05529},
  author = {Chalkidis, Ilias and Dai, Xiang and Fergadiotis, Manos and Malakasiotis, Prodromos and Elliott, Desmond},
  title = {An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification},
  publisher = {arXiv},
  year = {2022},
}