paper-with-me

Papers

Contrastive Document Representation Learning with Graph Attention Networks

2021-10-20 · Findings (EMNLP) 2021 11 · Peng Xu, Xinchi Chen, Xiaofei Ma, Zhiheng Huang, Bing Xiang

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.

📄 PDF Abstract BibTeX arXiv:2110.10778

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningDocument ClassificationGraph AttentionRepresentation LearningRetrieval

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Graph Contrastive Topic Model

2023-07-05 · Zheheng Luo, Lei Liu, Qianqian Xie, Sophia Ananiadou

Existing NTMs with contrastive learning suffer from the sample bias problem owing to the word frequency-based sampling strategy, which may result in false negative samples with similar semantics to the prototypes. In thi…

Contrastive LearningmodelRepresentation Learning

Skim-Aware Contrastive Learning for Efficient Document Representation

2025-12-30 · Waheed Ahmed Abro, Zied Bouraoui arxiv

Although transformer-based models have shown strong performance in word- and sentence-level tasks, effectively representing long documents, especially in fields like law and medicine, remains difficult. Sparse attention …

Natural Language InferenceContrastive Learning

Contrastive Hierarchical Discourse Graph for Scientific Document Summarization

2023-05-31 · Haopeng Zhang, Xiao Liu, Jiawei Zhang

The extended structural context has made scientific paper summarization a challenging task. This paper proposes CHANGES, a contrastive hierarchical graph neural network for extractive scientific paper summarization. CHAN…

Contrastive LearningDocument SummarizationGraph Neural NetworkScientific Document Summarization+1

StructCoh: Structured Contrastive Learning for Context-Aware Text Semantic Matching

2025-09-02 · Chao Xue, Ziyuan Gao arxiv

Text semantic matching requires nuanced understanding of both structural relationships and fine-grained semantic distinctions. While pre-trained language models excel at capturing token-level interactions, they often ove…

Contrastive LearningDependency Parsing

Attention-wise masked graph contrastive learning for predicting molecular property

2022-05-02 · Hui Liu, Yibiao Huang, Xuejun Liu, Lei Deng

Accurate and efficient prediction of the molecular properties of drugs is one of the fundamental problems in drug research and development. Recent advancements in representation learning have been shown to greatly improv…

Contrastive LearningGraph AttentionMolecular Property Predictionmolecular representation+3