paper-with-me

홈 › Papers

HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models

2021-10-08 · Tanya Goyal, Nazneen Fatema Rajani, Wenhao Liu, Wojciech Kryściński

Summarization systems make numerous "decisions" about summary properties during inference, e.g. degree of copying, specificity and length of outputs, etc. However, these are implicitly encoded within model parameters and specific styles cannot be enforced. To address this, we introduce HydraSum, a new summarization architecture that extends the single decoder framework of current models to a mixture-of-experts version with multiple decoders. We show that HydraSum's multiple decoders automatically learn contrasting summary styles when trained under the standard training objective without any extra supervision. Through experiments on three summarization datasets (CNN, Newsroom and XSum), we show that HydraSum provides a simple mechanism to obtain stylistically-diverse summaries by sampling from either individual decoders or their mixtures, outperforming baseline models. Finally, we demonstrate that a small modification to the gating strategy during training can enforce an even stricter style partitioning, e.g. high- vs low-abstractiveness or high- vs low-specificity, allowing users to sample from a larger area in the generation space and vary summary styles along multiple dimensions.

📄 PDF Abstract BibTeX arXiv:2110.04400

Code (1)

salesforce/hydra-sum 공식 구현 pytorch

Tasks

Abstractive Text SummarizationDecoderMixture-of-ExpertsSpecificityText Summarization

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 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 $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

HydraSum - Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models

2021-09-29 · Tanya Goyal, Nazneen Rajani, Wenhao Liu, Wojciech Maciej Kryscinski

Existing abstractive summarization models lack explicit control mechanisms that would allow users to influence the stylistic features of the model outputs. This results in generating generic summaries that do not cater t…

Abstractive Text SummarizationDecoderMixture-of-ExpertsSpecificity+1

Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals?

2024-01-18 · Marcio Fonseca, Shay B. Cohen

In this work, we investigate the controllability of large language models (LLMs) on scientific summarization tasks. We identify key stylistic and content coverage factors that characterize different types of summaries su…

Language ModelingLanguage ModellingLarge Language ModelReview Generation

BOOKSUM: A Collection of Datasets for Long-form Narrative Summarization

2022-01-16 · ACL ARR January 2022 1 · Anonymous

The majority of existing text summarization datasets include short-form source documents that lack long-range causal and temporal dependencies, and often contain strong layout and stylistic biases. While relevant, such …

Abstractive Text SummarizationFormLong-Form Narrative SummarizationText Summarization

Fourier-Attentive Representation Learning: A Fourier-Guided Framework for Few-Shot Generalization in Vision-Language Models

2025-12-04 · Hieu Dinh Trung Pham, Huy Minh Nhat Nguyen, Cuong Tuan Nguyen arxiv

Large-scale pre-trained Vision-Language Models (VLMs) have demonstrated strong few-shot learning capabilities. However, these methods typically learn holistic representations where an image's domain-invariant structure i…

Representation LearningFew-Shot Learning

BookSum: A Collection of Datasets for Long-form Narrative Summarization

2021-05-18 · Wojciech Kryściński, Nazneen Rajani, Divyansh Agarwal, Caiming Xiong 외

The majority of available text summarization datasets include short-form source documents that lack long-range causal and temporal dependencies, and often contain strong layout and stylistic biases. While relevant, such …

Abstractive Text SummarizationFormLong-Form Narrative SummarizationText Summarization