Search Results for author: Minwei Feng

Found 11 papers, 3 papers with code

CTC Blank Triggered Dynamic Layer-Skipping for Efficient CTC-based Speech Recognition

no code implementations4 Jan 2024 JunFeng Hou, Peiyao Wang, Jincheng Zhang, Meng Yang, Minwei Feng, Jingcheng Yin

Deploying end-to-end speech recognition models with limited computing resources remains challenging, despite their impressive performance.

Knowledge Distillation speech-recognition +1

Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator

1 code implementation24 May 2023 Ziwei He, Meng Yang, Minwei Feng, Jingcheng Yin, Xinbing Wang, Jingwen Leng, Zhouhan Lin

Many researchers have focused on designing new forms of self-attention or introducing new parameters to overcome this limitation, however a large portion of them prohibits the model to inherit weights from large pretrained models.

Abstractive Text Summarization Document Summarization +2

Local System Voting Feature for Machine Translation System Combination

no code implementations WS 2015 Markus Freitag, Jan-Thorsten Peter, Stephan Peitz, Minwei Feng, Hermann Ney

In this paper, we enhance the traditional confusion network system combination approach with an additional model trained by a neural network.

Machine Translation Sentence +1

GaDei: On Scale-up Training As A Service For Deep Learning

no code implementations18 Nov 2016 Wei Zhang, Minwei Feng, Yunhui Zheng, Yufei Ren, Yandong Wang, Ji Liu, Peng Liu, Bing Xiang, Li Zhang, Bo-Wen Zhou, Fei Wang

By evaluating the NLC workloads, we show that only the conservative hyper-parameter setup (e. g., small mini-batch size and small learning rate) can guarantee acceptable model accuracy for a wide range of customers.

Distributed Deep Learning for Question Answering

no code implementations3 Nov 2015 Minwei Feng, Bing Xiang, Bo-Wen Zhou

This paper is an empirical study of the distributed deep learning for question answering subtasks: answer selection and question classification.

Answer Selection General Classification

Applying Deep Learning to Answer Selection: A Study and An Open Task

2 code implementations7 Aug 2015 Minwei Feng, Bing Xiang, Michael R. Glass, Lidan Wang, Bo-Wen Zhou

We apply a general deep learning framework to address the non-factoid question answering task.

Answer Selection

Cannot find the paper you are looking for? You can Submit a new open access paper.