Kai Yu

is this you? claim profile

0 followers
Shanghai Jiao Tong University ∙ Baidu, Inc.

Research Professor at Computer Science and Engineering Department at Shanghai Jiao Tong University.

An Investigation on Different Underlying Quantization Schemes for Pre-trained Language Models

Recently, pre-trained language models like BERT have shown promising per...
10/14/2020 ∙ by Zihan Zhao, et al. ∙ 3 ∙ share

read it
CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking

In dialogue systems, a dialogue state tracker aims to accurately find a ...
09/22/2020 ∙ by Zhi Chen, et al. ∙ 0 ∙ share

read it
Dual Learning for Dialogue State Tracking

In task-oriented multi-turn dialogue systems, dialogue state refers to a...
09/22/2020 ∙ by Zhi Chen, et al. ∙ 0 ∙ share

read it
Structured Hierarchical Dialogue Policy with Graph Neural Networks

Dialogue policy training for composite tasks, such as restaurant reserva...
09/22/2020 ∙ by Zhi Chen, et al. ∙ 0 ∙ share

read it
Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management

The task-oriented spoken dialogue system (SDS) aims to assist a human us...
09/22/2020 ∙ by Zhi Chen, et al. ∙ 0 ∙ share

read it
Deep Reinforcement Learning for On-line Dialogue State Tracking

Dialogue state tracking (DST) is a crucial module in dialogue management...
09/22/2020 ∙ by Zhi Chen, et al. ∙ 0 ∙ share

read it
End-to-End Speaker-Dependent Voice Activity Detection

Voice activity detection (VAD) is an essential pre-processing step for t...
09/21/2020 ∙ by Yefei Chen, et al. ∙ 0 ∙ share

read it
Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding

Few-shot slot tagging becomes appealing for rapid domain transfer and ad...
09/21/2020 ∙ by Su Zhu, et al. ∙ 0 ∙ share

read it
Robust Spoken Language Understanding with RL-based Value Error Recovery

Spoken Language Understanding (SLU) aims to extract structured semantic ...
09/07/2020 ∙ by Chen Liu, et al. ∙ 0 ∙ share

read it
Modular End-to-end Automatic Speech Recognition Framework for Acoustic-to-word Model

End-to-end (E2E) systems have played a more and more important role in a...
07/31/2020 ∙ by Qi Liu, et al. ∙ 0 ∙ share

read it
Future Vector Enhanced LSTM Language Model for LVCSR

Language models (LM) play an important role in large vocabulary continuo...
07/31/2020 ∙ by Qi Liu, et al. ∙ 0 ∙ share

read it
An Investigation on Deep Learning with Beta Stabilizer

Artificial neural networks (ANN) have been used in many applications suc...
07/31/2020 ∙ by Qi Liu, et al. ∙ 0 ∙ share

read it
End-to-end spoofing detection with raw waveform CLDNNs

Albeit recent progress in speaker verification generates powerful models...
07/26/2020 ∙ by Heinrich Dinkel, et al. ∙ 0 ∙ share

read it
Quantum Criticism: A Tagged News Corpus Analysed for Sentiment and Named Entities

In this research, we continuously collect data from the RSS feeds of tra...
06/05/2020 ∙ by Ashwini Badgujar, et al. ∙ 0 ∙ share

read it
Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing

One daunting problem for semantic parsing is the scarcity of annotation....
05/27/2020 ∙ by Ruisheng Cao, et al. ∙ 0 ∙ share

read it
Jointly Encoding Word Confusion Network and Dialogue Context with BERT for Spoken Language Understanding

Spoken Language Understanding (SLU) converts hypotheses from automatic s...
05/24/2020 ∙ by Chen Liu, et al. ∙ 0 ∙ share

read it
Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders

Text simplification (TS) rephrases long sentences into simplified varian...
04/30/2020 ∙ by Yanbin Zhao, et al. ∙ 0 ∙ share

read it
Dual Learning for Semi-Supervised Natural Language Understanding

Natural language understanding (NLU) converts sentences into structured ...
04/26/2020 ∙ by Su Zhu, et al. ∙ 0 ∙ share

read it
Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking

Dialogue state tracking (DST) aims at estimating the current dialogue st...
04/07/2020 ∙ by Su Zhu, et al. ∙ 0 ∙ share

read it
Voice activity detection in the wild via weakly supervised sound event detection

Traditional supervised voice activity detection (VAD) methods work well ...
03/27/2020 ∙ by Heinrich Dinkel, et al. ∙ 0 ∙ share

read it
GPVAD: Towards noise robust voice activity detection via weakly supervised sound event detection

Traditional voice activity detection (VAD) methods work well in clean an...
03/27/2020 ∙ by Heinrich Dinkel, et al. ∙ 0 ∙ share

read it
Prior Knowledge Driven Label Embedding for Slot Filling in Natural Language Understanding

Traditional slot filling in natural language understanding (NLU) predict...
03/22/2020 ∙ by Su Zhu, et al. ∙ 0 ∙ share

read it
Depa: Self-supervised audio embedding for depression detection

Depression detection research has increased over the last few decades as...
10/29/2019 ∙ by Heinrich Dinkel, et al. ∙ 0 ∙ share

read it
Data Augmentation with Atomic Templates for Spoken Language Understanding

Spoken Language Understanding (SLU) converts user utterances into struct...
08/28/2019 ∙ by Zijian Zhao, et al. ∙ 0 ∙ share

read it
Semantic Parsing with Dual Learning

Semantic parsing converts natural language queries into structured logic...
07/10/2019 ∙ by Ruisheng Cao, et al. ∙ 0 ∙ share

read it
Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition

Recently, speaker embeddings extracted from a speaker discriminative dee...
06/18/2019 ∙ by Xu Xiang, et al. ∙ 0 ∙ share

read it
What does a Car-ssette tape tell?

Captioning has attracted much attention in image and video understanding...
05/31/2019 ∙ by Xuenan Xu, et al. ∙ 0 ∙ share

read it
AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning

Dialogue policy plays an important role in task-oriented spoken dialogue...
05/27/2019 ∙ by Lu Chen, et al. ∙ 5 ∙ share

read it
A Hierarchical Decoding Model For Spoken Language Understanding From Unaligned Data

Spoken language understanding (SLU) systems can be trained on two types ...
04/09/2019 ∙ by Zijian Zhao, et al. ∙ 0 ∙ share

read it
Duration robust sound event detection

Task 4 of the Dcase2018 challenge demonstrated that substantially more r...
04/08/2019 ∙ by Heinrich Dinkel, et al. ∙ 0 ∙ share

read it
Text-based Depression Detection: What Triggers An Alert

Recent advances in automatic depression detection mostly derive from mod...
04/08/2019 ∙ by Heinrich Dinkel, et al. ∙ 0 ∙ share

read it
Audio Caption: Listen and Tell

Increasing amount of research has shed light on machine perception of au...
02/25/2019 ∙ by Mengyue Wu, et al. ∙ 0 ∙ share

read it
End-to-End Monaural Multi-speaker ASR System without Pretraining

Recently, end-to-end models have become a popular approach as an alterna...
11/05/2018 ∙ by Xuankai Chang, et al. ∙ 0 ∙ share

read it
Towards Universal Dialogue State Tracking

Dialogue state tracking is the core part of a spoken dialogue system. It...
10/22/2018 ∙ by Liliang Ren, et al. ∙ 0 ∙ share

read it
Sequence Discriminative Training for Deep Learning based Acoustic Keyword Spotting

Speech recognition is a sequence prediction problem. Besides employing v...
08/02/2018 ∙ by Zhehuai Chen, et al. ∙ 0 ∙ share

read it
Deep Discriminant Analysis for i-vector Based Robust Speaker Recognition

Linear Discriminant Analysis (LDA) has been used as a standard post-proc...
05/03/2018 ∙ by Shuai Wang, et al. ∙ 0 ∙ share

read it
On Modular Training of Neural Acoustics-to-Word Model for LVCSR

End-to-end (E2E) automatic speech recognition (ASR) systems directly map...
03/03/2018 ∙ by Zhehuai Chen, et al. ∙ 0 ∙ share

read it
Concept Transfer Learning for Adaptive Language Understanding

Semantic transfer is an important problem of the language understanding ...
06/03/2017 ∙ by Su Zhu, et al. ∙ 0 ∙ share

read it
A Large-scale Distributed Video Parsing and Evaluation Platform

Visual surveillance systems have become one of the largest data sources ...
11/29/2016 ∙ by Kai Yu, et al. ∙ 0 ∙ share

read it
Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization

State-of-the-art methods treat pedestrian attribute recognition as a mul...
11/17/2016 ∙ by Kai Yu, et al. ∙ 0 ∙ share

read it
Encoder-decoder with Focus-mechanism for Sequence Labelling Based Spoken Language Understanding

This paper investigates the framework of encoder-decoder with attention ...
08/06/2016 ∙ by Su Zhu, et al. ∙ 0 ∙ share

read it
Text Flow: A Unified Text Detection System in Natural Scene Images

The prevalent scene text detection approach follows four sequential step...
04/23/2016 ∙ by Shangxuan Tian, et al. ∙ 0 ∙ share

read it
On Training Bi-directional Neural Network Language Model with Noise Contrastive Estimation

We propose to train bi-directional neural network language model(NNLM) w...
02/19/2016 ∙ by Tianxing He, et al. ∙ 0 ∙ share

read it
Bidirectional LSTM-CRF Models for Sequence Tagging

In this paper, we propose a variety of Long Short-Term Memory (LSTM) bas...
08/09/2015 ∙ by Zhiheng Huang, et al. ∙ 0 ∙ share

read it
Recurrent Polynomial Network for Dialogue State Tracking

Dialogue state tracking (DST) is a process to estimate the distribution ...
07/14/2015 ∙ by Kai Sun, et al. ∙ 0 ∙ share

read it
High-dimensional Joint Sparsity Random Effects Model for Multi-task Learning

Joint sparsity regularization in multi-task learning has attracted much ...
09/26/2013 ∙ by Krishnakumar Balasubramanian, et al. ∙ 0 ∙ share

read it
Large Scale Strongly Supervised Ensemble Metric Learning, with Applications to Face Verification and Retrieval

Learning Mahanalobis distance metrics in a high- dimensional feature spa...
12/25/2012 ∙ by Chang Huang, et al. ∙ 0 ∙ share

read it
Collaborative Ensemble Learning: Combining Collaborative and Content-Based Information Filtering via Hierarchical Bayes

Collaborative filtering (CF) and content-based filtering (CBF) have wide...
10/19/2012 ∙ by Kai Yu, et al. ∙ 0 ∙ share

read it
Smooth Sparse Coding via Marginal Regression for Learning Sparse Representations

We propose and analyze a novel framework for learning sparse representat...
10/03/2012 ∙ by Krishnakumar Balasubramanian, et al. ∙ 0 ∙ share

read it

Kai Yu

Featured Co-authors