no code implementations • NAACL (AutoSimTrans) 2021 • Shaolei Zhang, Yang Feng
Aiming at the robustness of ST, we first propose char-level simultaneous translation and applied wait-k policy on it.
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.
no code implementations • 17 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.
1 code implementation • 12 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.
1 code implementation • 27 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.
Ranked #2 on Question Answering on TruthfulQA
1 code implementation • 26 Feb 2024 • Zhaopeng Feng, Yan Zhang, Hao Li, Wenqiang Liu, Jun Lang, Yang Feng, Jian Wu, Zuozhu Liu
Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT).
1 code implementation • 20 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.
1 code implementation • 28 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.
1 code implementation • 17 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.
no code implementations • 16 Jan 2024 • Yang Feng, Zhaohui Sun, Chengcheng Wang, Xinyi Guo, Junyao Mei, Yueran Qi, Jing Liu, Junyu Zhang, Jixuan Wu, Xuepeng Zhan, Jiezhi Chen
Flash memory has been widely adopted as stand-alone memory and embedded memory due to its robust reliability.
1 code implementation • 10 Jan 2024 • Zijie Meng, Yan Zhang, Zhaopeng Feng, Yang Feng, Gaoang Wang, Joey Tianyi Zhou, Jian Wu, Zuozhu Liu
Large language models (LLMs) have shown impressive performance in various reasoning benchmarks with the emergence of Chain-of-Thought (CoT) and its derivative methods, particularly in tasks involving multi-choice questions (MCQs).
no code implementations • 29 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.
1 code implementation • 22 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.
no code implementations • 20 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.
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.
no code implementations • 26 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.
no code implementations • 23 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.
1 code implementation • 23 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.
no code implementations • 20 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.
1 code implementation • 20 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.
1 code implementation • 17 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.
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.
1 code implementation • NeurIPS 2023 • Zikai Xiao, Zihan Chen, Songshang Liu, Hualiang Wang, Yang Feng, Jin Hao, Joey Tianyi Zhou, Jian Wu, Howard Hao Yang, Zuozhu Liu
Data privacy and long-tailed distribution are the norms rather than the exception in many real-world tasks.
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.
no code implementations • 20 Sep 2023 • Yifu Zhang, Zuozhu Liu, Yang Feng, Renjing Xu
Accurate representation of tooth position is extremely important in treatment.
1 code implementation • 12 Sep 2023 • Shoutao Guo, Shaolei Zhang, Yang Feng
Simultaneous machine translation (SiMT) outputs translation while reading the source sentence.
no code implementations • 5 Jul 2023 • Jiaxiang Liu, Tianxiang Hu, Yang Feng, Wanghui Ding, Zuozhu Liu
In computer-assisted orthodontics, three-dimensional tooth models are required for many medical treatments.
no code implementations • 5 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.
1 code implementation • 19 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.
2 code implementations • 8 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.
no code implementations • 6 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.
1 code implementation • 25 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.
2 code implementations • 24 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.
1 code implementation • 22 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.
1 code implementation • 15 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
1 code implementation • 15 May 2023 • Qingkai Fang, Yang Feng
However, due to the differences between speech and text, there is always a gap between ST and MT.
1 code implementation • 31 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.
1 code implementation • 12 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.
1 code implementation • 1 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.
no code implementations • 29 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.
no code implementations • 30 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.
1 code implementation • 3 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.
1 code implementation • 30 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.
no code implementations • 29 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.
1 code implementation • 28 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.
1 code implementation • 22 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.
1 code implementation • 21 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.
1 code implementation • 20 Oct 2022 • Shaolei Zhang, Shoutao Guo, Yang Feng
In this paper, we propose a Wait-info Policy to balance source and target at the information level.
1 code implementation • 13 Oct 2022 • Zhe Yang, Qingkai Fang, Yang Feng
How to achieve neural machine translation with limited parallel data?
Contrastive Learning Low-Resource Neural Machine Translation +2
1 code implementation • 11 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.
1 code implementation • 8 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.
no code implementations • 30 Sep 2022 • Ye Tian, Haolei Weng, Yang Feng
Unsupervised learning has been widely used in many real-world applications.
no code implementations • 2 Sep 2022 • Zhiwen Jing, Ziliang Zhao, Yang Feng, Xiaochen Ma, Nan Wu, Shengqiao Kang, Cheng Yang, Yujia Zhang, Hao Guo
Supply Chain Platforms (SCPs) provide downstream industries with numerous raw materials.
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.
no code implementations • 16 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.
1 code implementation • ACL 2022 • Qingkai Fang, Rong Ye, Lei LI, Yang Feng, Mingxuan Wang
How to learn a better speech representation for end-to-end speech-to-text translation (ST) with limited labeled data?
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.
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.
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.
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.
no code implementations • 11 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.
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}.
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.
no code implementations • 14 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.
no code implementations • 8 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.
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.
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.
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.
1 code implementation • 4 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.
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.
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.
no code implementations • ACL 2021 • Yang Feng, Shuhao Gu, Dengji Guo, Zhengxin Yang, Chenze Shao
Meanwhile, we force the conventional decoder to simulate the behaviors of the seer decoder via knowledge distillation.
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.
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.
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.
no code implementations • 29 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.
no code implementations • 6 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.
no code implementations • 27 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.
no code implementations • 24 Apr 2021 • Yong Shan, Yang Feng, Chenze Shao
Non-Autoregressive Neural Machine Translation (NAT) has achieved significant inference speedup by generating all tokens simultaneously.
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.
no code implementations • 18 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.
1 code implementation • 7 Feb 2021 • Ye Tian, Yang Feng
Variable screening methods have been shown to be effective in dimension reduction under the ultra-high dimensional setting.
no code implementations • 20 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).
no code implementations • 6 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.
no code implementations • 1 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.
no code implementations • 23 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.
no code implementations • 7 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.
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.
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.
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.
no code implementations • 14 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.
no code implementations • WS 2020 • Haiyang Xue, Yang Feng, Shuhao Gu, Wei Chen
In this paper, we propose a method to handle the two problems so as to generate robust translation to ASR errors.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 16 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.
no code implementations • ACL 2020 • Yong Shan, Zekang Li, Jinchao Zhang, Fandong Meng, Yang Feng, Cheng Niu, Jie zhou
Recent studies in dialogue state tracking (DST) leverage historical information to determine states which are generally represented as slot-value pairs.
Ranked #6 on Multi-domain Dialogue State Tracking on MULTIWOZ 2.1
Dialogue State Tracking Multi-domain Dialogue State Tracking
no code implementations • 16 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.
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.
no code implementations • 26 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.
no code implementations • 21 Mar 2020 • Yang Feng, Yu Wang, Jiebo Luo
In this paper, we introduce a novel gating mechanism to deep neural networks.
Optical Flow Estimation Video-Based Person Re-Identification
no code implementations • 8 Mar 2020 • Yang Feng, Futang Peng, Xu Zhang, Wei Zhu, Shanfeng Zhang, Howard Zhou, Zhen Li, Tom Duerig, Shih-Fu Chang, Jiebo Luo
Therefore, we propose to distill the knowledge in multiple specialists into a universal embedding to solve this problem.
no code implementations • 11 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.
1 code implementation • 1 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).
1 code implementation • 30 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.
1 code implementation • 21 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.
no code implementations • 5 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.
no code implementations • 8 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
no code implementations • IJCNLP 2019 • Zhengxin Yang, Jinchao Zhang, Fandong Meng, Shuhao Gu, Yang Feng, Jie zhou
Context modeling is essential to generate coherent and consistent translation for Document-level Neural Machine Translations.
no code implementations • 31 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.
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.
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.
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.
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.
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.
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.
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.
no code implementations • 2 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
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.
no code implementations • EMNLP 2018 • Wen Zhang, Liang Huang, Yang Feng, Lei Shen, Qun Liu
Although neural machine translation has achieved promising results, it suffers from slow translation speed.
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.
no code implementations • 12 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.
no code implementations • 10 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.
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.
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.
no code implementations • 17 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.
9 code implementations • 12 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.
no code implementations • 7 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.
no code implementations • 27 Dec 2017 • Haolei Weng, Yang Feng
We consider a binary sequence generated by thresholding a hidden continuous sequence.
no code implementations • 28 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.
no code implementations • 12 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.
no code implementations • 6 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.
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.
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.
no code implementations • 6 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.
no code implementations • 28 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
no code implementations • 27 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.
no code implementations • 10 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.
no code implementations • 13 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.
no code implementations • 7 Jan 2015 • Jianqing Fan, Yang Feng, Lucy Xia
Measuring conditional dependence is an important topic in statistics with broad applications including graphical models.
no code implementations • 23 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.
no code implementations • 4 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.
no code implementations • 31 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.
no code implementations • 23 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.
no code implementations • 2 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.