1.5k citations · 1.6k across the 7 of their papers we have counts for
7 papers
CTC Blank Triggered Dynamic Layer-Skipping for Efficient CTC-based Speech Recognition
Junfeng Hou, Peiyao Wang, Jincheng Zhang +3
Deploying end-to-end speech recognition models with limited computing resources remains challenging, despite their impressive performance. Given the gradual increase in model size…
Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator
Ziwei He, Meng Yang, Minwei Feng +4
The transformer model is known to be computationally demanding, and prohibitively costly for long sequences, as the self-attention module uses a quadratic time and space complexity…
A Structured Self-attentive Sentence Embedding
Zhouhan Lin, Minwei Feng, Cicero Nogueira dos Santos +4
This paper proposes a new model for extracting an interpretable sentence embedding by introducing self-attention. Instead of using a vector, we use a 2-D matrix to represent the em…
Local System Voting Feature for Machine Translation System Combination
Markus Freitag, Jan-Thorsten Peter, Stephan Peitz +2
In this paper, we enhance the traditional confusion network system combination approach with an additional model trained by a neural network. This work is motivated by the fact tha…
GaDei: On Scale-up Training As A Service For Deep Learning
Wei Zhang, Minwei Feng, Yunhui Zheng +8
Deep learning (DL) training-as-a-service (TaaS) is an important emerging industrial workload. The unique challenge of TaaS is that it must satisfy a wide range of customers who hav…
Distributed Deep Learning for Question Answering
Minwei Feng, Bing Xiang, Bowen Zhou
This paper is an empirical study of the distributed deep learning for question answering subtasks: answer selection and question classification. Comparison studies of SGD, MSGD, AD…
Applying Deep Learning to Answer Selection: A Study and An Open Task
Minwei Feng, Bing Xiang, Michael R. Glass +2
We apply a general deep learning framework to address the non-factoid question answering task. Our approach does not rely on any linguistic tools and can be applied to different la…