|国家预印本平台
首页|Contrastive Document Representation Learning with Graph Attention Networks

Contrastive Document Representation Learning with Graph Attention Networks

Contrastive Document Representation Learning with Graph Attention Networks

来源:Arxiv_logoArxiv
英文摘要

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.

Xinchi Chen、Peng Xu、Xiaofei Ma、Zhiheng Huang、Bing Xiang

计算技术、计算机技术

Xinchi Chen,Peng Xu,Xiaofei Ma,Zhiheng Huang,Bing Xiang.Contrastive Document Representation Learning with Graph Attention Networks[EB/OL].(2021-10-20)[2025-07-25].https://arxiv.org/abs/2110.10778.点此复制

评论