paper-with-me

Papers

DynE: Dynamic Ensemble Decoding for Multi-Document Summarization

2020-06-15 · Chris Hokamp, Demian Gholipour Ghalandari, Nghia The Pham, John Glover

Sequence-to-sequence (s2s) models are the basis for extensive work in natural language processing. However, some applications, such as multi-document summarization, multi-modal machine translation, and the automatic post-editing of machine translation, require mapping a set of multiple distinct inputs into a single output sequence. Recent work has introduced bespoke architectures for these multi-input settings, and developed models which can handle increasingly longer inputs; however, the performance of special model architectures is limited by the available in-domain training data. In this work we propose a simple decoding methodology which ensembles the output of multiple instances of the same model on different inputs. Our proposed approach allows models trained for vanilla s2s tasks to be directly used in multi-input settings. This works particularly well when each of the inputs has significant overlap with the others, as when compressing a cluster of news articles about the same event into a single coherent summary, and we obtain state-of-the-art results on several multi-document summarization datasets.

📄 PDF Abstract BibTeX arXiv:2006.08748

Code (1)

chrishokamp/dynamic-transformer-ensembles 공식 구현 pytorch

Tasks

ArticlesAutomatic Post-EditingDocument SummarizationMachine TranslationMulti-Document SummarizationTranslation

Similar Papers 제목 키워드 기반

LSH-DynED: A Dynamic Ensemble Framework with LSH-Based Undersampling for Evolving Multi-Class Imbalanced Classification

2025-06-24 · Soheil Abadifard, Fazli Can

The classification of imbalanced data streams, which have unequal class distributions, is a key difficulty in machine learning, especially when dealing with multiple classes. While binary imbalanced data stream classific…

imbalanced classification

DynED: Dynamic Ensemble Diversification in Data Stream Classification

2023-08-21 · Proceedings of the 32nd ACM International Conference on Information and Knowledge Management 2023 10 · Soheil Abadifard, Sepehr Bakhshi, Sanaz Gheibuni, Fazli Can

Ensemble methods are commonly used in classification due to their remarkable performance. Achieving high accuracy in a data stream environment is a challenging task considering disruptive changes in the data distribution…

ClassificationDiversity

DyNet: The Dynamic Neural Network Toolkit

2017-01-15 · Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews 외

We describe DyNet, a toolkit for implementing neural network models based on dynamic declaration of network structure. In the static declaration strategy that is used in toolkits like Theano, CNTK, and TensorFlow, the us…

graph construction

DyNet: Dynamic Convolution for Accelerating Convolution Neural Networks

2019-09-25 · Kane Zhang, Jian Zhang, Qiang Wang, Zhao Zhong

Convolution operator is the core of convolutional neural networks (CNNs) and occupies the most computation cost. To make CNNs more efficient, many methods have been proposed to either design lightweight networks or compr…

CPU

DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks

2020-04-22 · Yikang Zhang, Jian Zhang, Qiang Wang, Zhao Zhong

Convolution operator is the core of convolutional neural networks (CNNs) and occupies the most computation cost. To make CNNs more efficient, many methods have been proposed to either design lightweight networks or compr…