Search Results for author: Yang Feng

Found 149 papers, 60 papers with code

Prediction Difference Regularization against Perturbation for Neural Machine Translation

no code implementations ACL 2022 Dengji Guo, Zhengrui Ma, Min Zhang, Yang Feng

Regularization methods applying input perturbation have drawn considerable attention and have been frequently explored for NMT tasks in recent years.

Machine Translation NMT +1

MedThink: Explaining Medical Visual Question Answering via Multimodal Decision-Making Rationale

no code implementations18 Apr 2024 Xiaotang Gai, Chenyi Zhou, Jiaxiang Liu, Yang Feng, Jian Wu, Zuozhu Liu

Moreover, we design a novel framework which finetunes lightweight pretrained generative models by incorporating medical decision-making rationales into the training process.

Decision Making Medical Visual Question Answering +2

Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Models

2 code implementations6 Apr 2024 Songtao Jiang, Yan Zhang, Chenyi Zhou, Yeying Jin, Yang Feng, Jian Wu, Zuozhu Liu

In this paper, we present a novel approach, Joint Visual and Text Prompting (VTPrompt), that employs fine-grained visual information to enhance the capability of MLLMs in VQA, especially for object-oriented perception.

Object Question Answering +1

Federated Transfer Learning with Differential Privacy

no code implementations17 Mar 2024 Mengchu Li, Ye Tian, Yang Feng, Yi Yu

By investigating the minimax rates and identifying the costs of privacy for these problems, we show that federated differential privacy is an intermediate privacy model between the well-established local and central models of differential privacy.

Federated Learning regression +1

Truth-Aware Context Selection: Mitigating the Hallucinations of Large Language Models Being Misled by Untruthful Contexts

1 code implementation12 Mar 2024 Tian Yu, Shaolei Zhang, Yang Feng

Although large language models (LLMs) have demonstrated impressive text generation capabilities, they are easily misled by the untruthful context provided by users or knowledge augmentation tools, thereby producing hallucinations.

Text Generation

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space

1 code implementation27 Feb 2024 Shaolei Zhang, Tian Yu, Yang Feng

During inference, by editing LLM's internal representations in truthful space, TruthX effectively enhances the truthfulness of LLMs.

Contrastive Learning Hallucination +5

SiLLM: Large Language Models for Simultaneous Machine Translation

1 code implementation20 Feb 2024 Shoutao Guo, Shaolei Zhang, Zhengrui Ma, Min Zhang, Yang Feng

We propose SiLLM, which delegates the two sub-tasks to separate agents, thereby incorporating LLM into SiMT.

Machine Translation Sentence +1

TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling

1 code implementation28 Jan 2024 Longxiang Liu, Xiuxing Li, Yang Feng

Specifically, we model the hierarchical policy as trees and utilize the similarity between trees to sample negative policy based on scheduled sampling, hoping the model to generate invariant responses under perturbations.

FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data

1 code implementation17 Jan 2024 Zikai Xiao, Zihan Chen, Liyinglan Liu, Yang Feng, Jian Wu, Wanlu Liu, Joey Tianyi Zhou, Howard Hao Yang, Zuozhu Liu

Federated Long-Tailed Learning (Fed-LT), a paradigm wherein data collected from decentralized local clients manifests a globally prevalent long-tailed distribution, has garnered considerable attention in recent times.

Personalized Federated Learning Representation Learning

MoD2T:Model-Data-Driven Motion-Static Object Tracking Method

no code implementations29 Dec 2023 Yang Feng, Liao Pan, Wu Di, Liu Bo, Zhang Xingle

This novel performance metric is designed to measure the accuracy of motion state classification, providing a comprehensive evaluation of MoD2T's performance.

Multi-Object Tracking Object

TSegFormer: 3D Tooth Segmentation in Intraoral Scans with Geometry Guided Transformer

1 code implementation22 Nov 2023 Huimin Xiong, Kunle Li, Kaiyuan Tan, Yang Feng, Joey Tianyi Zhou, Jin Hao, Haochao Ying, Jian Wu, Zuozhu Liu

Optical Intraoral Scanners (IOS) are widely used in digital dentistry to provide detailed 3D information of dental crowns and the gingiva.

Addressing the Length Bias Problem in Document-Level Neural Machine Translation

no code implementations20 Nov 2023 Zhuocheng Zhang, Shuhao Gu, Min Zhang, Yang Feng

To solve the length bias problem, we propose to improve the DNMT model in training method, attention mechanism, and decoding strategy.

Machine Translation Translation

Unified Segment-to-Segment Framework for Simultaneous Sequence Generation

no code implementations NeurIPS 2023 Shaolei Zhang, Yang Feng

To accomplish this, Seg2Seg introduces a latent segment as the pivot between source to target and explores all potential source-target mappings via the proposed expectation training, thereby learning the optimal moments for generating.

Machine Translation Multi-Task Learning +3

MO-YOLO: End-to-End Multiple-Object Tracking Method with YOLO and Decoder

no code implementations26 Oct 2023 Liao Pan, Yang Feng, Wu Di, Liu Bo, Zhang Xingle

In the field of multi-object tracking (MOT), recent Transformer based end-to-end models like MOTR have demonstrated exceptional performance on datasets such as DanceTracker.

Multi-Object Tracking Multiple Object Tracking +3

Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms

no code implementations23 Oct 2023 Ye Tian, Haolei Weng, Yang Feng

While supervised federated learning approaches have enjoyed significant success, the domain of unsupervised federated learning remains relatively underexplored.

Federated Learning

Non-autoregressive Streaming Transformer for Simultaneous Translation

1 code implementation23 Oct 2023 Zhengrui Ma, Shaolei Zhang, Shoutao Guo, Chenze Shao, Min Zhang, Yang Feng

Simultaneous machine translation (SiMT) models are trained to strike a balance between latency and translation quality.

Machine Translation Translation

Simultaneous Machine Translation with Tailored Reference

no code implementations20 Oct 2023 Shoutao Guo, Shaolei Zhang, Yang Feng

Training the model with ground-truth at low latency may introduce forced anticipations, whereas utilizing reference consistent with the source word order at high latency results in performance degradation.

Machine Translation Sentence +1

Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation

1 code implementation20 Oct 2023 Wenyu Guo, Qingkai Fang, Dong Yu, Yang Feng

Multimodal machine translation (MMT) simultaneously takes the source sentence and a relevant image as input for translation.

Multimodal Machine Translation Sentence +2

Enhancing Neural Machine Translation with Semantic Units

1 code implementation17 Oct 2023 Langlin Huang, Shuhao Gu, Zhuocheng Zhang, Yang Feng

Conventional neural machine translation (NMT) models typically use subwords and words as the basic units for model input and comprehension.

Machine Translation NMT +2

DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation

1 code implementation NeurIPS 2023 Qingkai Fang, Yan Zhou, Yang Feng

However, due to the presence of linguistic and acoustic diversity, the target speech follows a complex multimodal distribution, posing challenges to achieving both high-quality translations and fast decoding speeds for S2ST models.

Knowledge Distillation Speech-to-Speech Translation +1

Towards Distribution-Agnostic Generalized Category Discovery

1 code implementation NeurIPS 2023 Jianhong Bai, Zuozhu Liu, Hualiang Wang, Ruizhe Chen, Lianrui Mu, Xiaomeng Li, Joey Tianyi Zhou, Yang Feng, Jian Wu, Haoji Hu

In this paper, we formally define a more realistic task as distribution-agnostic generalized category discovery (DA-GCD): generating fine-grained predictions for both close- and open-set classes in a long-tailed open-world setting.

Contrastive Learning Transfer Learning

Glancing Future for Simultaneous Machine Translation

1 code implementation12 Sep 2023 Shoutao Guo, Shaolei Zhang, Yang Feng

Simultaneous machine translation (SiMT) outputs translation while reading the source sentence.

Machine Translation Sentence +1

A ChatGPT Aided Explainable Framework for Zero-Shot Medical Image Diagnosis

no code implementations5 Jul 2023 Jiaxiang Liu, Tianxiang Hu, Yan Zhang, Xiaotang Gai, Yang Feng, Zuozhu Liu

Recent advances in pretrained vision-language models (VLMs) such as CLIP have shown great performance for zero-shot natural image recognition and exhibit benefits in medical applications.

Image Classification Medical Image Classification

BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models

1 code implementation19 Jun 2023 Shaolei Zhang, Qingkai Fang, Zhuocheng Zhang, Zhengrui Ma, Yan Zhou, Langlin Huang, Mengyu Bu, Shangtong Gui, Yunji Chen, Xilin Chen, Yang Feng

To minimize human workload, we propose to transfer the capabilities of language generation and instruction following from English to other languages through an interactive translation task.

Instruction Following Text Generation +1

On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning

2 code implementations8 Jun 2023 Jianhong Bai, Zuozhu Liu, Hualiang Wang, Jin Hao, Yang Feng, Huanpeng Chu, Haoji Hu

Recent work shows that the long-tailed learning performance could be boosted by sampling extra in-domain (ID) data for self-supervised training, however, large-scale ID data which can rebalance the minority classes are expensive to collect.

Long-tail Learning Representation Learning +1

Benchmarking Robustness of AI-Enabled Multi-sensor Fusion Systems: Challenges and Opportunities

no code implementations6 Jun 2023 Xinyu Gao, Zhijie Wang, Yang Feng, Lei Ma, Zhenyu Chen, Baowen Xu

Multi-Sensor Fusion (MSF) based perception systems have been the foundation in supporting many industrial applications and domains, such as self-driving cars, robotic arms, and unmanned aerial vehicles.

Benchmarking Depth Completion +5

End-to-End Simultaneous Speech Translation with Differentiable Segmentation

1 code implementation25 May 2023 Shaolei Zhang, Yang Feng

Therefore, learning to segment the speech inputs at those moments that are beneficial for the translation model to produce high-quality translation is the key to SimulST.

Segmentation Translation

CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation

2 code implementations24 May 2023 Yan Zhou, Qingkai Fang, Yang Feng

End-to-end speech translation (ST) is the task of translating speech signals in the source language into text in the target language.

Machine Translation Translation

Learning Optimal Policy for Simultaneous Machine Translation via Binary Search

1 code implementation22 May 2023 Shoutao Guo, Shaolei Zhang, Yang Feng

Simultaneous machine translation (SiMT) starts to output translation while reading the source sentence and needs a precise policy to decide when to output the generated translation.

Machine Translation Sentence +1

Back Translation for Speech-to-text Translation Without Transcripts

1 code implementation15 May 2023 Qingkai Fang, Yang Feng

Motivated by the remarkable success of back translation in MT, we develop a back translation algorithm for ST (BT4ST) to synthesize pseudo ST data from monolingual target data.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Understanding and Bridging the Modality Gap for Speech Translation

1 code implementation15 May 2023 Qingkai Fang, Yang Feng

However, due to the differences between speech and text, there is always a gap between ST and MT.

Machine Translation Multi-Task Learning +1

Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness

1 code implementation31 Mar 2023 Ye Tian, Yuqi Gu, Yang Feng

With a known intrinsic dimension, we propose two algorithms that are \textit{adaptive} to the similarity structure and \textit{robust} to outlier tasks under both MTL and TL settings.

Multi-Task Learning

Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translation

1 code implementation12 Mar 2023 Zhengrui Ma, Chenze Shao, Shangtong Gui, Min Zhang, Yang Feng

Non-autoregressive translation (NAT) reduces the decoding latency but suffers from performance degradation due to the multi-modality problem.

Machine Translation Sentence +1

Hidden Markov Transformer for Simultaneous Machine Translation

1 code implementation1 Mar 2023 Shaolei Zhang, Yang Feng

Simultaneous machine translation (SiMT) outputs the target sequence while receiving the source sequence, and hence learning when to start translating each target token is the core challenge for SiMT task.

Machine Translation Translation

OrthoGAN:High-Precision Image Generation for Teeth Orthodontic Visualization

no code implementations29 Dec 2022 Feihong Shen, Jingjing Liu, Haizhen Li, Bing Fang, Chenglong Ma, Jin Hao, Yang Feng, Youyi Zheng

We design a multi-modal encoder-decoder based generative model to synthesize identity-preserving frontal facial images with aligned teeth.

Image Generation

Rephrasing the Reference for Non-Autoregressive Machine Translation

no code implementations30 Nov 2022 Chenze Shao, Jinchao Zhang, Jie zhou, Yang Feng

In response to this problem, we introduce a rephraser to provide a better training target for NAT by rephrasing the reference sentence according to the NAT output.

Machine Translation Sentence +1

Continual Learning of Neural Machine Translation within Low Forgetting Risk Regions

1 code implementation3 Nov 2022 Shuhao Gu, Bojie Hu, Yang Feng

Specifically, we propose two methods to search the low forgetting risk regions, which are based on the curvature of loss and the impacts of the parameters on the model output, respectively.

Continual Learning Domain Adaptation +2

Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues

1 code implementation30 Oct 2022 Jiao Ou, Jinchao Zhang, Yang Feng, Jie zhou

The dialogue data admits a wide variety of responses for a given dialogue history, especially responses with different semantics.

counterfactual Counterfactual Inference +1

TFormer: 3D Tooth Segmentation in Mesh Scans with Geometry Guided Transformer

no code implementations29 Oct 2022 Huimin Xiong, Kunle Li, Kaiyuan Tan, Yang Feng, Joey Tianyi Zhou, Jin Hao, Zuozhu Liu

Optical Intra-oral Scanners (IOS) are widely used in digital dentistry, providing 3-Dimensional (3D) and high-resolution geometrical information of dental crowns and the gingiva.

Multi-Task Learning Segmentation

Improving Zero-Shot Multilingual Translation with Universal Representations and Cross-Mappings

1 code implementation28 Oct 2022 Shuhao Gu, Yang Feng

The many-to-many multilingual neural machine translation can translate between language pairs unseen during training, i. e., zero-shot translation.

Machine Translation Translation

Information-Transport-based Policy for Simultaneous Translation

1 code implementation22 Oct 2022 Shaolei Zhang, Yang Feng

Simultaneous translation (ST) outputs translation while receiving the source inputs, and hence requires a policy to determine whether to translate a target token or wait for the next source token.

Machine Translation Translation

Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation

1 code implementation21 Oct 2022 Shoutao Guo, Shaolei Zhang, Yang Feng

Compared to the fixed policy, the adaptive policy achieves better latency-quality tradeoffs by adopting a flexible translation policy.

Machine Translation Sentence +1

Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation

1 code implementation11 Oct 2022 Chenze Shao, Zhengrui Ma, Yang Feng

Non-autoregressive models achieve significant decoding speedup in neural machine translation but lack the ability to capture sequential dependency.

Machine Translation Translation

Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation

1 code implementation8 Oct 2022 Chenze Shao, Yang Feng

We extend the alignment space to non-monotonic alignments to allow for the global word reordering and further consider all alignments that overlap with the target sentence.

Machine Translation Sentence +1

One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translation

1 code implementation NAACL 2022 Chenze Shao, Xuanfu Wu, Yang Feng

Non-autoregressive neural machine translation (NAT) suffers from the multi-modality problem: the source sentence may have multiple correct translations, but the loss function is calculated only according to the reference sentence.

Knowledge Distillation Machine Translation +2

DDAC-SpAM: A Distributed Algorithm for Fitting High-dimensional Sparse Additive Models with Feature Division and Decorrelation

no code implementations16 May 2022 Yifan He, Ruiyang Wu, Yong Zhou, Yang Feng

The effectiveness and efficiency of the proposed algorithm are demonstrated through theoretical analysis and empirical results on both synthetic and real data.

Additive models feature selection +1

Neural Machine Translation with Phrase-Level Universal Visual Representations

1 code implementation ACL 2022 Qingkai Fang, Yang Feng

Multimodal machine translation (MMT) aims to improve neural machine translation (NMT) with additional visual information, but most existing MMT methods require paired input of source sentence and image, which makes them suffer from shortage of sentence-image pairs.

Multimodal Machine Translation NMT +2

Modeling Dual Read/Write Paths for Simultaneous Machine Translation

1 code implementation ACL 2022 Shaolei Zhang, Yang Feng

According to duality constraints, the read/write path in source-to-target and target-to-source SiMT models can be mapped to each other.

Machine Translation Sentence +1

Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Framework

no code implementations ACL 2022 Shaolei Zhang, Yang Feng

Simultaneous machine translation (SiMT) starts translating while receiving the streaming source inputs, and hence the source sentence is always incomplete during translating.

Machine Translation Position +2

Gaussian Multi-head Attention for Simultaneous Machine Translation

1 code implementation Findings (ACL) 2022 Shaolei Zhang, Yang Feng

For SiMT policy, GMA models the aligned source position of each target word, and accordingly waits until its aligned position to start translating.

Machine Translation Position +1

AI-enabled Automatic Multimodal Fusion of Cone-Beam CT and Intraoral Scans for Intelligent 3D Tooth-Bone Reconstruction and Clinical Applications

no code implementations11 Mar 2022 Jin Hao, Jiaxiang Liu, Jin Li, Wei Pan, Ruizhe Chen, Huimin Xiong, Kaiwei Sun, Hangzheng Lin, Wanlu Liu, Wanghui Ding, Jianfei Yang, Haoji Hu, Yueling Zhang, Yang Feng, Zeyu Zhao, Huikai Wu, Youyi Zheng, Bing Fang, Zuozhu Liu, Zhihe Zhao

Here, we present a Deep Dental Multimodal Analysis (DDMA) framework consisting of a CBCT segmentation model, an intraoral scan (IOS) segmentation model (the most accurate digital dental model), and a fusion model to generate 3D fused crown-root-bone structures with high fidelity and accurate occlusal and dentition information.


Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation

1 code implementation ACL 2022 Chenze Shao, Yang Feng

The underlying cause is that training samples do not get balanced training in each model update, so we name this problem \textit{imbalanced training}.

Continual Learning Knowledge Distillation +2

Relational Surrogate Loss Learning

1 code implementation ICLR 2022 Tao Huang, Zekang Li, Hua Lu, Yong Shan, Shusheng Yang, Yang Feng, Fei Wang, Shan You, Chang Xu

Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e. g., average precision and F1 score.

Image Classification Machine Reading Comprehension +3

Mental Health Assessment for the Chatbots

no code implementations14 Jan 2022 Yong Shan, Jinchao Zhang, Zekang Li, Yang Feng, Jie zhou

Previous researches on dialogue system assessment usually focus on the quality evaluation (e. g. fluency, relevance, etc) of responses generated by the chatbots, which are local and technical metrics.


Neyman-Pearson Multi-class Classification via Cost-sensitive Learning

no code implementations8 Nov 2021 Ye Tian, Yang Feng

In this work, we study the multi-class NP problem by connecting it to the CS problem and propose two algorithms.

Classification Multi-class Classification

Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model

no code implementations Findings (EMNLP) 2021 Shaolei Zhang, Yang Feng

Cross-attention is an important component of neural machine translation (NMT), which is always realized by dot-product attention in previous methods.

Machine Translation NMT +2

Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy

1 code implementation EMNLP 2021 Shaolei Zhang, Yang Feng

Simultaneous machine translation (SiMT) generates translation before reading the entire source sentence and hence it has to trade off between translation quality and latency.

Machine Translation Sentence +1

Mixup Decoding for Diverse Machine Translation

no code implementations Findings (EMNLP) 2021 Jicheng Li, Pengzhi Gao, Xuanfu Wu, Yang Feng, Zhongjun He, Hua Wu, Haifeng Wang

To further improve the faithfulness and diversity of the translations, we propose two simple but effective approaches to select diverse sentence pairs in the training corpus and adjust the interpolation weight for each pair correspondingly.

Machine Translation Sentence +1

Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmark

1 code implementation4 Sep 2021 Zhengcong Fei, Zekang Li, Jinchao Zhang, Yang Feng, Jie zhou

Compared to previous dialogue tasks, MOD is much more challenging since it requires the model to understand the multimodal elements as well as the emotions behind them.

Importance-based Neuron Allocation for Multilingual Neural Machine Translation

1 code implementation ACL 2021 Wanying Xie, Yang Feng, Shuhao Gu, Dong Yu

Multilingual neural machine translation with a single model has drawn much attention due to its capability to deal with multiple languages.

General Knowledge Machine Translation +1

Sequence-Level Training for Non-Autoregressive Neural Machine Translation

1 code implementation CL (ACL) 2021 Chenze Shao, Yang Feng, Jinchao Zhang, Fandong Meng, Jie zhou

Non-Autoregressive Neural Machine Translation (NAT) removes the autoregressive mechanism and achieves significant decoding speedup through generating target words independently and simultaneously.

Machine Translation NMT +2

GTM: A Generative Triple-Wise Model for Conversational Question Generation

no code implementations ACL 2021 Lei Shen, Fandong Meng, Jinchao Zhang, Yang Feng, Jie zhou

Generating some appealing questions in open-domain conversations is an effective way to improve human-machine interactions and lead the topic to a broader or deeper direction.

Question Generation Question-Generation

Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances

1 code implementation ACL 2021 Zekang Li, Jinchao Zhang, Zhengcong Fei, Yang Feng, Jie zhou

Nowadays, open-domain dialogue models can generate acceptable responses according to the historical context based on the large-scale pre-trained language models.

Dialogue Evaluation Dialogue Generation

Addressing Inquiries about History: An Efficient and Practical Framework for Evaluating Open-domain Chatbot Consistency

1 code implementation Findings (ACL) 2021 Zekang Li, Jinchao Zhang, Zhengcong Fei, Yang Feng, Jie zhou

Employing human judges to interact with chatbots on purpose to check their capacities is costly and low-efficient, and difficult to get rid of subjective bias.

Chatbot Natural Language Inference

Transfer Learning under High-dimensional Generalized Linear Models

no code implementations29 May 2021 Ye Tian, Yang Feng

In this work, we study the transfer learning problem under high-dimensional generalized linear models (GLMs), which aim to improve the fit on target data by borrowing information from useful source data.

Transfer Learning Vocal Bursts Intensity Prediction

Machine Collaboration

no code implementations6 May 2021 Qingfeng Liu, Yang Feng

We propose a new ensemble framework for supervised learning, called machine collaboration (MaC), using a collection of base machines for prediction tasks.

SE-DAE: Style-Enhanced Denoising Auto-Encoder for Unsupervised Text Style Transfer

no code implementations27 Apr 2021 Jicheng Li, Yang Feng, Jiao Ou

Moreover, to alleviate the conflict between the targets of the conventional denoising procedure and the style transfer task, we propose another novel style denoising mechanism, which is more compatible with the target of the style transfer task.

Denoising Sentence +3

Modeling Coverage for Non-Autoregressive Neural Machine Translation

no code implementations24 Apr 2021 Yong Shan, Yang Feng, Chenze Shao

Non-Autoregressive Neural Machine Translation (NAT) has achieved significant inference speedup by generating all tokens simultaneously.

Machine Translation Sentence +1

Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation

1 code implementation NAACL 2021 Shuhao Gu, Yang Feng, Wanying Xie

Domain Adaptation is widely used in practical applications of neural machine translation, which aims to achieve good performance on both the general-domain and in-domain.

Domain Adaptation Knowledge Distillation +2

Learning to Select Context in a Hierarchical and Global Perspective for Open-domain Dialogue Generation

no code implementations18 Feb 2021 Lei Shen, Haolan Zhan, Xin Shen, Yang Feng

Open-domain multi-turn conversations mainly have three features, which are hierarchical semantic structure, redundant information, and long-term dependency.

Dialogue Generation Informativeness

RaSE: A Variable Screening Framework via Random Subspace Ensembles

1 code implementation7 Feb 2021 Ye Tian, Yang Feng

Variable screening methods have been shown to be effective in dimension reduction under the ultra-high dimensional setting.

Dimensionality Reduction

WeChat AI & ICT's Submission for DSTC9 Interactive Dialogue Evaluation Track

no code implementations20 Jan 2021 Zekang Li, Zongjia Li, Jinchao Zhang, Yang Feng, Jie zhou

We participate in the DSTC9 Interactive Dialogue Evaluation Track (Gunasekara et al. 2020) sub-task 1 (Knowledge Grounded Dialogue) and sub-task 2 (Interactive Dialogue).

Dialogue Evaluation Language Modelling +1

The Interplay of Demographic Variables and Social Distancing Scores in Deep Prediction of U.S. COVID-19 Cases

no code implementations6 Jan 2021 Francesca Tang, Yang Feng, Hamza Chiheb, Jianqing Fan

With the severity of the COVID-19 outbreak, we characterize the nature of the growth trajectories of counties in the United States using a novel combination of spectral clustering and the correlation matrix.


Knowledge Distillation based Ensemble Learning for Neural Machine Translation

no code implementations1 Jan 2021 Chenze Shao, Meng Sun, Yang Feng, Zhongjun He, Hua Wu, Haifeng Wang

Under this framework, we introduce word-level ensemble learning and sequence-level ensemble learning for neural machine translation, where sequence-level ensemble learning is capable of aggregating translation models with different decoding strategies.

Ensemble Learning Knowledge Distillation +2

Future-Guided Incremental Transformer for Simultaneous Translation

no code implementations23 Dec 2020 Shaolei Zhang, Yang Feng, Liangyou Li

Simultaneous translation (ST) starts translations synchronously while reading source sentences, and is used in many online scenarios.

Knowledge Distillation Translation

Spectral clustering via adaptive layer aggregation for multi-layer networks

no code implementations7 Dec 2020 Sihan Huang, Haolei Weng, Yang Feng

One of the fundamental problems in network analysis is detecting community structure in multi-layer networks, of which each layer represents one type of edge information among the nodes.

Clustering Community Detection

Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation

no code implementations COLING 2020 Shuhao Gu, Yang Feng

The investigation on the modules of the NMT model shows that some modules have tight relation with the general-domain knowledge while some other modules are more essential in the domain adaptation.

Domain Adaptation Machine Translation +2

Generating Diverse Translation from Model Distribution with Dropout

no code implementations EMNLP 2020 Xuanfu Wu, Yang Feng, Chenze Shao

Despite the improvement of translation quality, neural machine translation (NMT) often suffers from the lack of diversity in its generation.

Machine Translation NMT +2

Token-level Adaptive Training for Neural Machine Translation

1 code implementation EMNLP 2020 Shuhao Gu, Jinchao Zhang, Fandong Meng, Yang Feng, Wanying Xie, Jie zhou, Dong Yu

The vanilla NMT model usually adopts trivial equal-weighted objectives for target tokens with different frequencies and tends to generate more high-frequency tokens and less low-frequency tokens compared with the golden token distribution.

Machine Translation NMT +1

Universal Model for Multi-Domain Medical Image Retrieval

no code implementations14 Jul 2020 Yang Feng, Yubao Liu, Jiebo Luo

Usually, one image retrieval model is only trained to handle images from one modality or one source.

Medical Image Retrieval Retrieval

RaSE: Random Subspace Ensemble Classification

no code implementations16 Jun 2020 Ye Tian, Yang Feng

In addition, we show that in a high-dimensional framework, the number of random subspaces needs to be very large to guarantee that a subspace covering signals is selected.

Classification General Classification

Nested Model Averaging on Solution Path for High-dimensional Linear Regression

no code implementations16 May 2020 Yang Feng, Qing-Feng Liu

We study the nested model averaging method on the solution path for a high-dimensional linear regression problem.

regression Vocal Bursts Intensity Prediction

CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation

no code implementations ACL 2020 Lei Shen, Yang Feng

Emotion-controllable response generation is an attractive and valuable task that aims to make open-domain conversations more empathetic and engaging.

Response Generation

Towards Multimodal Response Generation with Exemplar Augmentation and Curriculum Optimization

no code implementations26 Apr 2020 Zeyang Lei, Zekang Li, Jinchao Zhang, Fandong Meng, Yang Feng, Yujiu Yang, Cheng Niu, Jie zhou

Furthermore, to facilitate the convergence of Gaussian mixture prior and posterior distributions, we devise a curriculum optimization strategy to progressively train the model under multiple training criteria from easy to hard.

Response Generation

Imbalanced classification: a paradigm-based review

no code implementations11 Feb 2020 Yang Feng, Min Zhou, Xin Tong

For each pair of resampling techniques and classification methods, we use simulation studies and a real data set on credit card fraud to study the performance under different evaluation metrics.

Binary Classification Classification +2

Bridging Text and Video: A Universal Multimodal Transformer for Video-Audio Scene-Aware Dialog

1 code implementation1 Feb 2020 Zekang Li, Zongjia Li, Jinchao Zhang, Yang Feng, Cheng Niu, Jie zhou

Audio-Visual Scene-Aware Dialog (AVSD) is a task to generate responses when chatting about a given video, which is organized as a track of the 8th Dialog System Technology Challenge (DSTC8).

Dialogue Generation Multi-Task Learning

Modeling Fluency and Faithfulness for Diverse Neural Machine Translation

1 code implementation30 Nov 2019 Yang Feng, Wanying Xie, Shuhao Gu, Chenze Shao, Wen Zhang, Zhengxin Yang, Dong Yu

Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the probability of each prediction to approach a 0-1 distribution.

Machine Translation Translation

Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation

1 code implementation21 Nov 2019 Chenze Shao, Jinchao Zhang, Yang Feng, Fandong Meng, Jie zhou

Non-Autoregressive Neural Machine Translation (NAT) achieves significant decoding speedup through generating target words independently and simultaneously.

Machine Translation Sentence +1

Improving Bidirectional Decoding with Dynamic Target Semantics in Neural Machine Translation

no code implementations5 Nov 2019 Yong Shan, Yang Feng, Jinchao Zhang, Fandong Meng, Wen Zhang

Generally, Neural Machine Translation models generate target words in a left-to-right (L2R) manner and fail to exploit any future (right) semantics information, which usually produces an unbalanced translation.

Machine Translation Translation

Software Engineering Practice in the Development of Deep Learning Applications

no code implementations8 Oct 2019 Xufan Zhang, Yilin Yang, Yang Feng, Zhenyu Chen

Specifically, we asked the respondents to identify lacks and challenges in the practice of the development life cycle of DL applications.

Software Engineering

Improving Multi-Head Attention with Capsule Networks

no code implementations31 Aug 2019 Shuhao Gu, Yang Feng

Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of translation and consequently hinders the further improvement of translation performance.

Clustering Machine Translation +1

Incremental Transformer with Deliberation Decoder for Document Grounded Conversations

2 code implementations ACL 2019 Zekang Li, Cheng Niu, Fandong Meng, Yang Feng, Qian Li, Jie zhou

Document Grounded Conversations is a task to generate dialogue responses when chatting about the content of a given document.

Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation

3 code implementations ACL 2019 Chenze Shao, Yang Feng, Jinchao Zhang, Fandong Meng, Xilin Chen, Jie zhou

Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer model through discarding the autoregressive mechanism and generating target words independently, which fails to exploit the target sequential information.

Machine Translation Sentence +1

Modeling Semantic Relationship in Multi-turn Conversations with Hierarchical Latent Variables

no code implementations ACL 2019 Lei Shen, Yang Feng, Haolan Zhan

Multi-turn conversations consist of complex semantic structures, and it is still a challenge to generate coherent and diverse responses given previous utterances.

Bridging the Gap between Training and Inference for Neural Machine Translation

no code implementations ACL 2019 Wen Zhang, Yang Feng, Fandong Meng, Di You, Qun Liu

Neural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words.

Machine Translation NMT +2

Spatio-temporal Video Re-localization by Warp LSTM

no code implementations CVPR 2019 Yang Feng, Lin Ma, Wei Liu, Jiebo Luo

The need for efficiently finding the video content a user wants is increasing because of the erupting of user-generated videos on the Web.

Retrieval Video Retrieval

Improving Domain Adaptation Translation with Domain Invariant and Specific Information

no code implementations NAACL 2019 Shuhao Gu, Yang Feng, Qun Liu

Besides, we add a discriminator to the shared encoder and employ adversarial training for the whole model to reinforce the performance of information separation and machine translation simultaneously.

Domain Adaptation Machine Translation +1

Unsupervised Image Captioning

1 code implementation CVPR 2019 Yang Feng, Lin Ma, Wei Liu, Jiebo Luo

Instead of relying on manually labeled image-sentence pairs, our proposed model merely requires an image set, a sentence corpus, and an existing visual concept detector.

Image Captioning Sentence

Improving the Robustness of Speech Translation

no code implementations2 Nov 2018 Xiang Li, Haiyang Xue, Wei Chen, Yang Liu, Yang Feng, Qun Liu

Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech recognition (ASR) system due to the enormous errors in the source.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +5

Greedy Search with Probabilistic N-gram Matching for Neural Machine Translation

1 code implementation EMNLP 2018 Chenze Shao, Yang Feng, Xilin Chen

Neural machine translation (NMT) models are usually trained with the word-level loss using the teacher forcing algorithm, which not only evaluates the translation improperly but also suffers from exposure bias.

Machine Translation NMT +1

Video Re-localization

1 code implementation ECCV 2018 Yang Feng, Lin Ma, Wei Liu, Tong Zhang, Jiebo Luo

We first exploit and reorganize the videos in ActivityNet to form a new dataset for video re-localization research, which consists of about 10, 000 videos of diverse visual appearances associated with localized boundary information.

Copy Detection

A likelihood-ratio type test for stochastic block models with bounded degrees

no code implementations12 Jul 2018 Mingao Yuan, Yang Feng, Zuofeng Shang

A fundamental problem in network data analysis is to test Erd\"{o}s-R\'{e}nyi model $\mathcal{G}\left(n,\frac{a+b}{2n}\right)$ versus a bisection stochastic block model $\mathcal{G}\left(n,\frac{a}{n},\frac{b}{n}\right)$, where $a, b>0$ are constants that represent the expected degrees of the graphs and $n$ denotes the number of nodes.

Community Detection Stochastic Block Model

Pairwise Covariates-adjusted Block Model for Community Detection

no code implementations10 Jul 2018 Sihan Huang, Jiajin Sun, Yang Feng

It is shown that both the coefficient estimates of the covariates and the community assignments are consistent under suitable sparsity conditions.

Clustering Community Detection +3

Knowledge Diffusion for Neural Dialogue Generation

1 code implementation ACL 2018 Shuman Liu, Hongshen Chen, Zhaochun Ren, Yang Feng, Qun Liu, Dawei Yin

Our empirical study on a real-world dataset prove that our model is capable of generating meaningful, diverse and natural responses for both factoid-questions and knowledge grounded chi-chats.

Dialogue Generation Question Answering +1

Refining Source Representations with Relation Networks for Neural Machine Translation

no code implementations COLING 2018 Wen Zhang, Jiawei Hu, Yang Feng, Qun Liu

Although neural machine translation with the encoder-decoder framework has achieved great success recently, it still suffers drawbacks of forgetting distant information, which is an inherent disadvantage of recurrent neural network structure, and disregarding relationship between source words during encoding step.

Machine Translation Memorization +2

Large-Scale Model Selection with Misspecification

no code implementations17 Mar 2018 Emre Demirkaya, Yang Feng, Pallavi Basu, Jinchi Lv

Our new information criterion characterizes the impacts of both model misspecification and high dimensionality on model selection.

Model Selection

Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications

9 code implementations12 Feb 2018 Haowen Xu, Wenxiao Chen, Nengwen Zhao, Zeyan Li, Jiahao Bu, Zhihan Li, Ying Liu, Youjian Zhao, Dan Pei, Yang Feng, Jie Chen, Zhaogang Wang, Honglin Qiao

To ensure undisrupted business, large Internet companies need to closely monitor various KPIs (e. g., Page Views, number of online users, and number of orders) of its Web applications, to accurately detect anomalies and trigger timely troubleshooting/mitigation.

Unsupervised Anomaly Detection

Neyman-Pearson classification: parametrics and sample size requirement

no code implementations7 Feb 2018 Xin Tong, Lucy Xia, Jiacheng Wang, Yang Feng

In this work, we employ the parametric linear discriminant analysis (LDA) model and propose a new parametric thresholding algorithm, which does not need the minimum sample size requirements on class $0$ observations and thus is suitable for small sample applications such as rare disease diagnosis.

Binary Classification Classification +3

On the estimation of correlation in a binary sequence model

no code implementations27 Dec 2017 Haolei Weng, Yang Feng

We consider a binary sequence generated by thresholding a hidden continuous sequence.

Nonparametric Independence Screening via Favored Smoothing Bandwidth

no code implementations28 Nov 2017 Yang Feng, Yi-Chao Wu, Leonard Stefanski

As a first step, we propose a fast screening method based on the favored smoothing bandwidth of the marginal local constant regression.

Model Selection regression

Refining Source Representations with Relation Networks for Neural Machine Translation

no code implementations12 Sep 2017 Wen Zhang, Jiawei Hu, Yang Feng, Qun Liu

Although neural machine translation (NMT) with the encoder-decoder framework has achieved great success in recent times, it still suffers from some drawbacks: RNNs tend to forget old information which is often useful and the encoder only operates through words without considering word relationship.

Machine Translation NMT +2

Information-Propogation-Enhanced Neural Machine Translation by Relation Model

no code implementations6 Sep 2017 Wen Zhang, Jiawei Hu, Yang Feng, Qun Liu

Even though sequence-to-sequence neural machine translation (NMT) model have achieved state-of-art performance in the recent fewer years, but it is widely concerned that the recurrent neural network (RNN) units are very hard to capture the long-distance state information, which means RNN can hardly find the feature with long term dependency as the sequence becomes longer.

Machine Translation NMT +4

Memory-augmented Neural Machine Translation

no code implementations EMNLP 2017 Yang Feng, Shiyue Zhang, Andi Zhang, Dong Wang, Andrew Abel

Neural machine translation (NMT) has achieved notable success in recent times, however it is also widely recognized that this approach has limitations with handling infrequent words and word pairs.

Machine Translation NMT +1

Flexible and Creative Chinese Poetry Generation Using Neural Memory

no code implementations ACL 2017 Jiyuan Zhang, Yang Feng, Dong Wang, Yang Wang, Andrew Abel, Shiyue Zhang, Andi Zhang

It has been shown that Chinese poems can be successfully generated by sequence-to-sequence neural models, particularly with the attention mechanism.

Do They All Look the Same? Deciphering Chinese, Japanese and Koreans by Fine-Grained Deep Learning

no code implementations6 Oct 2016 Yu Wang, Haofu Liao, Yang Feng, Xiangyang Xu, Jiebo Luo

We find that Chinese, Japanese and Koreans do exhibit substantial differences in certain attributes, such as bangs, smiling, and bushy eyebrows.

Attribute Marketing

Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition

no code implementations28 Sep 2016 Zhiyuan Tang, Ying Shi, Dong Wang, Yang Feng, Shiyue Zhang

Recurrent neural networks (RNNs) have shown clear superiority in sequence modeling, particularly the ones with gated units, such as long short-term memory (LSTM) and gated recurrent unit (GRU).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Collaborative Learning for Language and Speaker Recognition

no code implementations27 Sep 2016 Lantian Li, Zhiyuan Tang, Dong Wang, Andrew Abel, Yang Feng, Shiyue Zhang

This paper presents a unified model to perform language and speaker recognition simultaneously and altogether.

Speaker Recognition

When Do Luxury Cars Hit the Road? Findings by A Big Data Approach

no code implementations10 May 2016 Yang Feng, Jiebo Luo

Based on the recognition results, we present a data-driven analysis on the relationship between car makes and their appearing times, with implications on lifestyles.


Neyman-Pearson Classification under High-Dimensional Settings

no code implementations13 Aug 2015 Anqi Zhao, Yang Feng, Lie Wang, Xin Tong

Most existing binary classification methods target on the optimization of the overall classification risk and may fail to serve some real-world applications such as cancer diagnosis, where users are more concerned with the risk of misclassifying one specific class than the other.

Binary Classification Classification +4

A Projection Based Conditional Dependence Measure with Applications to High-dimensional Undirected Graphical Models

no code implementations7 Jan 2015 Jianqing Fan, Yang Feng, Lucy Xia

Measuring conditional dependence is an important topic in statistics with broad applications including graphical models.

Model Selection in High-Dimensional Misspecified Models

no code implementations23 Dec 2014 Pallavi Basu, Yang Feng, Jinchi Lv

Model selection is indispensable to high-dimensional sparse modeling in selecting the best set of covariates among a sequence of candidate models.

Model Selection Vocal Bursts Intensity Prediction

How Many Communities Are There?

no code implementations4 Dec 2014 Diego Franco Saldana, Yi Yu, Yang Feng

Stochastic blockmodels and variants thereof are among the most widely used approaches to community detection for social networks and relational data.

Clustering Community Detection +1

Feature Augmentation via Nonparametrics and Selection (FANS) in High Dimensional Classification

no code implementations31 Dec 2013 Jianqing Fan, Yang Feng, Jiancheng Jiang, Xin Tong

We motivate FANS by generalizing the Naive Bayes model, writing the log ratio of joint densities as a linear combination of those of marginal densities.

Additive models General Classification +1

Likelihood Adaptively Modified Penalties

no code implementations23 Aug 2013 Yang Feng, Tengfei Li, Zhiliang Ying

A new family of penalty functions, adaptive to likelihood, is introduced for model selection in general regression models.

Model Selection regression

APPLE: Approximate Path for Penalized Likelihood Estimators

no code implementations2 Nov 2012 Yi Yu, Yang Feng

In high-dimensional data analysis, penalized likelihood estimators are shown to provide superior results in both variable selection and parameter estimation.

Variable Selection

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