Search Results for author:
Found 98 papers, 33 papers with code
Glyph Enhanced Chinese Character Pre-Training for Lexical Sememe Prediction
Sememes are defined as the atomic units to describe the semantic meaning of concepts.
The AISP-SJTU Simultaneous Translation System for IWSLT 2022
This paper describes AISP-SJTU’s submissions for the IWSLT 2022 Simultaneous Translation task.
CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset
Furthermore, we present CSS, a large-scale CrosS-Schema Chinese text-to-SQL dataset, to carry on corresponding studies.
TeCS: A Dataset and Benchmark for Tense Consistency of Machine Translation
Tense inconsistency frequently occurs in machine translation.
PointGPT: Auto-regressively Generative Pre-training from Point Clouds
Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks.
Ranked #1 on
Few-Shot 3D Point Cloud Classification
on ModelNet40 10-way (20-shot)
(using extra training data)
3D Part Segmentation
Few-Shot 3D Point Cloud Classification
+1
Mobile-Env: A Universal Platform for Training and Evaluation of Mobile Interaction
To help the research of InfoUI interaction, a novel platform Mobile-Env is presented in this paper.
DiffVoice: Text-to-Speech with Latent Diffusion
In this work, we present DiffVoice, a novel text-to-speech model based on latent diffusion.
DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder
Additionally, we propose a novel method for generating continuous video frames with the DDIM image decoder trained on individual frames, eliminating the need for modelling the joint distribution of consecutive frames directly.
TrFedDis: Trusted Federated Disentangling Network for Non-IID Domain Feature
To the best of our knowledge, our proposed TrFedDis is the first work to develop an FL approach based on evidential uncertainty combined with feature disentangling, which enhances the performance and reliability of FL in non-IID domain features.
On the Structural Generalization in Text-to-SQL
Exploring the generalization of a text-to-SQL parser is essential for a system to automatically adapt the real-world databases.
Spectral Efficiency Analysis of Uplink-Downlink Decoupled Access in C-V2X Networks
The uplink (UL)/downlink (DL) decoupled access has been emerging as a novel access architecture to improve the performance gains in cellular networks.
Spectral Efficiency Analysis of Uplink-Downlink Decoupled Access in C-V2X Networks
Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images
Specifically, aiming at improving the model's ability to learn the complex pathological features of retinal edema lesions in OCT images, we develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module of our newly designed.
EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance
Specifically, instead of being guided with a one-hot vector for the specified emotion, EmoDiff is guided with a soft label where the value of the specified emotion and \textit{Neutral} is set to $\alpha$ and $1-\alpha$ respectively.
BER: Balanced Error Rate For Speaker Diarization
DER is the primary metric to evaluate diarization performance while facing a dilemma: the errors in short utterances or segments tend to be overwhelmed by longer ones.
OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue
The second phase is to fine-tune the pretrained model on the TOD data.
DFM: Dialogue Foundation Model for Universal Large-Scale Dialogue-Oriented Task Learning
In this work, we aim to build a unified dialogue foundation model (DFM) which can be used to solve massive diverse dialogue tasks.
D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat
In a depression-diagnosis-directed clinical session, doctors initiate a conversation with ample emotional support that guides the patients to expose their symptoms based on clinical diagnosis criteria.
META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI
However, this API-based architecture greatly limits the information-searching capability of intelligent assistants and may even lead to task failure if TOD-specific APIs are not available or the task is too complicated to be executed by the provided APIs.
TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages
Recently, the structural reading comprehension (SRC) task on web pages has attracted increasing research interests.
Climate and Weather: Inspecting Depression Detection via Emotion Recognition
Automatic depression detection has attracted increasing amount of attention but remains a challenging task.
UniDU: Towards A Unified Generative Dialogue Understanding Framework
With the development of pre-trained language models, remarkable success has been witnessed in dialogue understanding (DU).
VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature
The mainstream neural text-to-speech(TTS) pipeline is a cascade system, including an acoustic model(AM) that predicts acoustic feature from the input transcript and a vocoder that generates waveform according to the given acoustic feature.
Audio-text Retrieval in Context
Using pre-trained audio features and a descriptor-based aggregation method, we build our contextual audio-text retrieval system.
Unsupervised word-level prosody tagging for controllable speech synthesis
Although word-level prosody modeling in neural text-to-speech (TTS) has been investigated in recent research for diverse speech synthesis, it is still challenging to control speech synthesis manually without a specific reference.
Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRF
In this paper, we propose to improve prototypical networks with vector projection distance and abstract triangular Conditional Random Field (CRF) for the few-shot NLU.
Exploring Separable Attention for Multi-Contrast MR Image Super-Resolution
Our SANet could explore the areas of high-intensity and low-intensity regions in the "forward" and "reverse" directions with the help of the auxiliary contrast, while learning clearer anatomical structure and edge information for the SR of a target-contrast MR image.
THE SJTU SYSTEM FOR DCASE2021 CHALLENGE TASK 6: AUDIO CAPTIONING BASED ON ENCODER PRE-TRAINING AND REINFORCEMENT LEARNING
This report proposes an audio captioning system for the Detection and Classification of Acoustic Scenes and Events (DCASE) 2021 challenge task Task 6.
Ranked #2 on
Audio captioning
on Clotho
(using extra training data)
Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL
A dual learning approach is also proposed for the utterance rewrite model to address the data sparsity problem.
LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations
This work aims to tackle the challenging heterogeneous graph encoding problem in the text-to-SQL task.
ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser
Given a database schema, Text-to-SQL aims to translate a natural language question into the corresponding SQL query.
Quantum Dimensionality Reduction by Linear Discriminant Analysis
In this paper, we present a quantum algorithm and a quantum circuit to efficiently perform linear discriminant analysis (LDA) for dimensionality reduction.
Dimensionality Reduction
Quantum Physics
LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching
Additionally, we adopt the word lattice graph as input to maintain multi-granularity information.
Rich Prosody Diversity Modelling with Phone-level Mixture Density Network
Generating natural speech with diverse and smooth prosody pattern is a challenging task.
WebSRC: A Dataset for Web-Based Structural Reading Comprehension
In this paper, we introduce the task of structural reading comprehension (SRC) on web.
Towards duration robust weakly supervised sound event detection
Our model outperforms other approaches on the DCASE2018 and URBAN-SED datasets without requiring prior duration knowledge.
Data Augmentation
Sound Event Detection
Sound
Audio and Speech Processing
A relic sketch extraction framework based on detail-aware hierarchical deep network
For the fine extraction stage, we design a new multiscale U-Net (MSU-Net) to effectively remove disease noise and refine the sketch.
A 3D Non-stationary MmWave Channel Model for Vacuum Tube Ultra-High-Speed Train Channels
As a potential development direction of future transportation, the vacuum tube ultra-high-speed train (UHST) wireless communication systems have newly different channel characteristics from existing high-speed train (HST) scenarios.
An Investigation on Different Underlying Quantization Schemes for Pre-trained Language Models
Recently, pre-trained language models like BERT have shown promising performance on multiple natural language processing tasks.
CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking
In dialogue systems, a dialogue state tracker aims to accurately find a compact representation of the current dialogue status, based on the entire dialogue history.
Dual Learning for Dialogue State Tracking
In task-oriented multi-turn dialogue systems, dialogue state refers to a compact representation of the user goal in the context of dialogue history.
Structured Hierarchical Dialogue Policy with Graph Neural Networks
A novel ComNet is proposed to model the structure of a hierarchical agent.
Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management
The task-oriented spoken dialogue system (SDS) aims to assist a human user in accomplishing a specific task (e. g., hotel booking).
Deep Reinforcement Learning for On-line Dialogue State Tracking
To the best of our knowledge, this is the first effort to optimize the DST module within DRL framework for on-line task-oriented spoken dialogue systems.
Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding
Few-shot slot tagging becomes appealing for rapid domain transfer and adaptation, motivated by the tremendous development of conversational dialogue systems.
Robust Spoken Language Understanding with RL-based Value Error Recovery
The framework consists of a slot tagging model and a rule-based value error recovery module.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
An Investigation on Deep Learning with Beta Stabilizer
It is concluded that beta stabilizer parameters can reduce the sensitivity of learning rate with almost the same performance on DNN with relu activation function and LSTM.
Future Vector Enhanced LSTM Language Model for LVCSR
For the speech recognition rescoring, although the proposed LSTM LM obtains very slight gains, the new model seems obtain the great complementary with the conventional LSTM LM.
Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks
We also adopt graph attention networks with higher-order neighborhood information to encode the rich structure in AMR graphs.
Neural Graph Matching Networks for Chinese Short Text Matching
Chinese short text matching usually employs word sequences rather than character sequences to get better performance.
Quantum Criticism: A Tagged News Corpus Analysed for Sentiment and Named Entities
In this research, we continuously collect data from the RSS feeds of traditional news sources.
Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing
One daunting problem for semantic parsing is the scarcity of annotation.
Jointly Encoding Word Confusion Network and Dialogue Context with BERT for Spoken Language Understanding
In this paper, a novel BERT based SLU model (WCN-BERT SLU) is proposed to encode WCNs and the dialogue context jointly.
Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders
When modeling simple and complex sentences with autoencoders, we introduce different types of noise into the training process.
Dual Learning for Semi-Supervised Natural Language Understanding
The framework is composed of dual pseudo-labeling and dual learning method, which enables an NLU model to make full use of data (labeled and unlabeled) through a closed-loop of the primal and dual tasks.
Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking
In this paper, a novel context and schema fusion network is proposed to encode the dialogue context and schema graph by using internal and external attention mechanisms.
Ranked #8 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.0
Dialogue State Tracking
Multi-domain Dialogue State Tracking
Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks
For multi-domain DST, the data sparsity problem is also a major obstacle due to the increased number of state candidates.
Ranked #12 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.1
Voice activity detection in the wild via weakly supervised sound event detection
We proposed two GPVAD models, one full (GPV-F), trained on 527 Audioset sound events, and one binary (GPV-B), only distinguishing speech and noise.
Sound Audio and Speech Processing
Prior Knowledge Driven Label Embedding for Slot Filling in Natural Language Understanding
The proposed approaches are evaluated on three datasets.
Data Augmentation with Atomic Templates for Spoken Language Understanding
The atomic templates produce exemplars for fine-grained constituents of semantic representations.
Semantic Parsing with Dual Learning
Semantic parsing converts natural language queries into structured logical forms.
Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition
The proposed approach can achieve the state-of-the-art performance, with 25% ~ 30% equal error rate (EER) reduction on both tasks when compared to strong baselines using cross entropy loss with softmax, obtaining 2. 238% EER on VoxCeleb1 test set and 2. 761% EER on SITW core-core test set, respectively.
Audio Caption in a Car Setting with a Sentence-Level Loss
Captioning has attracted much attention in image and video understanding while a small amount of work examines audio captioning.
AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning
Experiments show that AgentGraph models significantly outperform traditional reinforcement learning approaches on most of the 18 tasks of the PyDial benchmark.
A Hierarchical Decoding Model For Spoken Language Understanding From Unaligned Data
In the paper, we focus on spoken language understanding from unaligned data whose annotation is a set of act-slot-value triples.
Duration robust sound event detection
Task 4 of the Dcase2018 challenge demonstrated that substantially more research is needed for a real-world application of sound event detection.
Sound Audio and Speech Processing
Text-based depression detection on sparse data
Previous text-based depression detection is commonly based on large user-generated data.
Audio Caption: Listen and Tell
A baseline encoder-decoder model is provided for both English and Mandarin.
End-to-End Monaural Multi-speaker ASR System without Pretraining
The experiments demonstrate that the proposed methods can improve the performance of the end-to-end model in separating the overlapping speech and recognizing the separated streams.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Towards Universal Dialogue State Tracking
Dialogue state tracking is the core part of a spoken dialogue system.
Sequence Discriminative Training for Deep Learning based Acoustic Keyword Spotting
The few studies on sequence discriminative training for KWS are limited for fixed vocabulary or LVCSR based methods and have not been compared to the state-of-the-art deep learning based KWS approaches.
Structured Dialogue Policy with Graph Neural Networks
The proposed structured deep reinforcement learning is based on graph neural networks (GNN), which consists of some sub-networks, each one for a node on a directed graph.
Cost-Sensitive Active Learning for Dialogue State Tracking
Dialogue state tracking (DST), when formulated as a supervised learning problem, relies on labelled data.
Binarized LSTM Language Model
Although excellent performance is obtained for large vocabulary tasks, tremendous memory consumption prohibits the use of LSTM LM in low-resource devices.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
On Modular Training of Neural Acoustics-to-Word Model for LVCSR
Finally, modules are integrated into an acousticsto-word model (A2W) and jointly optimized using acoustic data to retain the advantage of sequence modeling.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Affordable On-line Dialogue Policy Learning
The key to building an evolvable dialogue system in real-world scenarios is to ensure an affordable on-line dialogue policy learning, which requires the on-line learning process to be safe, efficient and economical.
Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning
Hand-crafted rules and reinforcement learning (RL) are two popular choices to obtain dialogue policy.
Concept Transfer Learning for Adaptive Language Understanding
Concept definition is important in language understanding (LU) adaptation since literal definition difference can easily lead to data sparsity even if different data sets are actually semantically correlated.
On-line Dialogue Policy Learning with Companion Teaching
On-line dialogue policy learning is the key for building evolvable conversational agent in real world scenarios.
A Large-scale Distributed Video Parsing and Evaluation Platform
Visual surveillance systems have become one of the largest data sources of Big Visual Data in real world.
Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization
Based on GoogLeNet, firstly, a set of mid-level attribute features are discovered by novelly designed detection layers, where a max-pooling based weakly-supervised object detection technique is used to train these layers with only image-level labels without the need of bounding box annotations of pedestrian attributes.
Encoder-decoder with Focus-mechanism for Sequence Labelling Based Spoken Language Understanding
This paper investigates the framework of encoder-decoder with attention for sequence labelling based spoken language understanding.
Text Flow: A Unified Text Detection System in Natural Scene Images
With character candidates detected by cascade boosting, the min-cost flow network model integrates the last three sequential steps into a single process which solves the error accumulation problem at both character level and text line level effectively.
On Training Bi-directional Neural Network Language Model with Noise Contrastive Estimation
We propose to train bi-directional neural network language model(NNLM) with noise contrastive estimation(NCE).
Bidirectional LSTM-CRF Models for Sequence Tagging
It can also use sentence level tag information thanks to a CRF layer.
Ranked #1 on
Named Entity Recognition (NER)
on FindVehicle
Recurrent Polynomial Network for Dialogue State Tracking
Dialogue state tracking (DST) is a process to estimate the distribution of the dialogue states as a dialogue progresses.
Deep Multiple Instance Learning for Image Classification and Auto-Annotation
The recent development in learning deep representations has demonstrated its wide applications in traditional vision tasks like classification and detection.
Communication Efficient Distributed Machine Learning with the Parameter Server
This paper describes a third-generation parameter server framework for distributed machine learning.
High-dimensional Joint Sparsity Random Effects Model for Multi-task Learning
The traditional convex formulation employs the group Lasso relaxation to achieve joint sparsity across tasks.
Large Scale Strongly Supervised Ensemble Metric Learning, with Applications to Face Verification and Retrieval
Learning Mahanalobis distance metrics in a high- dimensional feature space is very difficult especially when structural sparsity and low rank are enforced to improve com- putational efficiency in testing phase.
Deep Coding Network
This paper proposes a principled extension of the traditional single-layer flat sparse coding scheme, where a two-layer coding scheme is derived based on theoretical analysis of nonlinear functional approximation that extends recent results for local coordinate coding.
Nonlinear Learning using Local Coordinate Coding
This paper introduces a new method for semi-supervised learning on high dimensional nonlinear manifolds, which includes a phase of unsupervised basis learning and a phase of supervised function learning.
Deep Learning with Kernel Regularization for Visual Recognition
In this paper we focus on training deep neural networks for visual recognition tasks.
Stochastic Relational Models for Large-scale Dyadic Data using MCMC
Stochastic relational models provide a rich family of choices for learning and predicting dyadic data between two sets of entities.
Gaussian Process Models for Link Analysis and Transfer Learning
In this paper we develop a Gaussian process (GP) framework to model a collection of reciprocal random variables defined on the \emph{edges} of a network.
Predictive Matrix-Variate t Models
It is becoming increasingly important to learn from a partially-observed random matrix and predict its missing elements.
