English

Contrastive Document Representation Learning with Graph Attention Networks

Computation and Language 2021-10-22 v1

Abstract

Recent progress in pretrained Transformer-based language models has shown great success in learning contextual representation of text. However, due to the quadratic self-attention complexity, most of the pretrained Transformers models can only handle relatively short text. It is still a challenge when it comes to modeling very long documents. In this work, we propose to use a graph attention network on top of the available pretrained Transformers model to learn document embeddings. This graph attention network allows us to leverage the high-level semantic structure of the document. In addition, based on our graph document model, we design a simple contrastive learning strategy to pretrain our models on a large amount of unlabeled corpus. Empirically, we demonstrate the effectiveness of our approaches in document classification and document retrieval tasks.

Keywords

Cite

@article{arxiv.2110.10778,
  title  = {Contrastive Document Representation Learning with Graph Attention Networks},
  author = {Peng Xu and Xinchi Chen and Xiaofei Ma and Zhiheng Huang and Bing Xiang},
  journal= {arXiv preprint arXiv:2110.10778},
  year   = {2021}
}

Comments

Findings of EMNLP 2021

R2 v1 2026-06-24T07:03:22.739Z