paper-with-me

홈 › Papers

HDT: Hierarchical Document Transformer

2024-07-11 · Haoyu He, Markus Flicke, Jan Buchmann, Iryna Gurevych, Andreas Geiger

In this paper, we propose the Hierarchical Document Transformer (HDT), a novel sparse Transformer architecture tailored for structured hierarchical documents. Such documents are extremely important in numerous domains, including science, law or medicine. However, most existing solutions are inefficient and fail to make use of the structure inherent to documents. HDT exploits document structure by introducing auxiliary anchor tokens and redesigning the attention mechanism into a sparse multi-level hierarchy. This approach facilitates information exchange between tokens at different levels while maintaining sparsity, thereby enhancing computational and memory efficiency while exploiting the document structure as an inductive bias. We address the technical challenge of implementing HDT's sample-dependent hierarchical attention pattern by developing a novel sparse attention kernel that considers the hierarchical structure of documents. As demonstrated by our experiments, utilizing structural information present in documents leads to faster convergence, higher sample efficiency and better performance on downstream tasks.

📄 PDF Abstract BibTeX arXiv:2407.08330

Code (0)

등록된 구현이 없습니다.

Tasks

Inductive Bias

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
Multi-Head Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Similar Papers 제목 키워드 기반

Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling

2021-06-02 · ACL 2021 5 · Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang

Transformer is important for text modeling. However, it has difficulty in handling long documents due to the quadratic complexity with input text length. In order to handle this problem, we propose a hierarchical interac…

Document EmbeddingSentence

Hierarchical Graph Topic Modeling with Topic Tree-based Transformer

2025-02-17 · Delvin Ce Zhang, Menglin Yang, Xiaobao Wu, Jiasheng Zhang 외

Textual documents are commonly connected in a hierarchical graph structure where a central document links to others with an exponentially growing connectivity. Though Hyperbolic Graph Neural Networks (HGNNs) excel at cap…

SpecificityTopic Models

An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification

2022-10-11 · Ilias Chalkidis, Xiang Dai, Manos Fergadiotis, Prodromos Malakasiotis 외

Non-hierarchical sparse attention Transformer-based models, such as Longformer and Big Bird, are popular approaches to working with long documents. There are clear benefits to these approaches compared to the original Tr…

Document ClassificationGPU

Hierarchical Multi-modal Transformer for Cross-modal Long Document Classification

2024-07-14 · Tengfei Liu, Yongli Hu, Junbin Gao, Yanfeng Sun 외

Long Document Classification (LDC) has gained significant attention recently. However, multi-modal data in long documents such as texts and images are not being effectively utilized. Prior studies in this area have attem…

Document ClassificationSentence

Parallel Hierarchical Transformer with Attention Alignment for Abstractive Multi-Document Summarization

2022-08-16 · Ye Ma, Lu Zong

In comparison to single-document summarization, abstractive Multi-Document Summarization (MDS) brings challenges on the representation and coverage of its lengthy and linked sources. This study develops a Parallel Hierar…

Document SummarizationMulti-Document Summarization