paper-with-me

홈 › Papers

Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons

2019-09-04 · IJCNLP 2019 11 · Jie Hao, Xing Wang, Shuming Shi, Jinfeng Zhang, Zhaopeng Tu

Recent studies have shown that a hybrid of self-attention networks (SANs) and recurrent neural networks (RNNs) outperforms both individual architectures, while not much is known about why the hybrid models work. With the belief that modeling hierarchical structure is an essential complementary between SANs and RNNs, we propose to further enhance the strength of hybrid models with an advanced variant of RNNs - Ordered Neurons LSTM (ON-LSTM), which introduces a syntax-oriented inductive bias to perform tree-like composition. Experimental results on the benchmark machine translation task show that the proposed approach outperforms both individual architectures and a standard hybrid model. Further analyses on targeted linguistic evaluation and logical inference tasks demonstrate that the proposed approach indeed benefits from a better modeling of hierarchical structure.

📄 PDF Abstract BibTeX arXiv:1909.01562

Code (0)

등록된 구현이 없습니다.

Tasks

Inductive BiasMachine TranslationTranslation

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Tree Transformer: Integrating Tree Structures into Self-Attention

2019-09-14 · IJCNLP 2019 11 · Yau-Shian Wang, Hung-Yi Lee, Yun-Nung Chen

Pre-training Transformer from large-scale raw texts and fine-tuning on the desired task have achieved state-of-the-art results on diverse NLP tasks. However, it is unclear what the learned attention captures. The attenti…

Language ModelingLanguage Modelling

Tree-structured Attention with Hierarchical Accumulation

2020-02-19 · ICLR 2020 1 · Xuan-Phi Nguyen, Shafiq Joty, Steven C. H. Hoi, Richard Socher

Incorporating hierarchical structures like constituency trees has been shown to be effective for various natural language processing (NLP) tasks. However, it is evident that state-of-the-art (SOTA) sequence-based models …

text-classificationText ClassificationTranslation

Self-Attention Networks Can Process Bounded Hierarchical Languages

2021-05-24 · ACL 2021 5 · Shunyu Yao, Binghui Peng, Christos Papadimitriou, Karthik Narasimhan

Despite their impressive performance in NLP, self-attention networks were recently proved to be limited for processing formal languages with hierarchical structure, such as $\mathsf{Dyck}_k$, the language consisting of w…

Hard Attention

Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion

2025-04-04 · Junkai Zhang, Bin Li, Shoujun Zhou, Yue Du

Medical Visual Question Answering (Med-VQA) answers clinical questions using medical images, aiding diagnosis. Designing the MedVQA system holds profound importance in assisting clinical diagnosis and enhancing diagnosti…

DiagnosticMedical Visual Question AnsweringQuestion AnsweringVisual Question Answering+1

Multiresolution Transformer Networks: Recurrence is Not Essential for Modeling Hierarchical Structure

2019-08-27 · Vikas K. Garg, Inderjit S. Dhillon, Hsiang-Fu Yu

The architecture of Transformer is based entirely on self-attention, and has been shown to outperform models that employ recurrence on sequence transduction tasks such as machine translation. The superior performance of …

Machine TranslationTranslation