no code implementations • WMT (EMNLP) 2020 • Shuangzhi Wu, Xing Wang, Longyue Wang, Fangxu Liu, Jun Xie, Zhaopeng Tu, Shuming Shi, Mu Li
This paper describes Tencent Neural Machine Translation systems for the WMT 2020 news translation tasks.
no code implementations • WMT (EMNLP) 2021 • Xing Wang, Zhaopeng Tu, Shuming Shi
This paper describes the Tencent AI Lab submission of the WMT2021 shared task on biomedical translation in eight language directions: English-German, English-French, English-Spanish and English-Russian.
no code implementations • WMT (EMNLP) 2021 • Longyue Wang, Mu Li, Fangxu Liu, Shuming Shi, Zhaopeng Tu, Xing Wang, Shuangzhi Wu, Jiali Zeng, Wen Zhang
Based on our success in the last WMT, we continuously employed advanced techniques such as large batch training, data selection and data filtering.
1 code implementation • WMT (EMNLP) 2020 • Xing Wang, Zhaopeng Tu, Longyue Wang, Shuming Shi
This paper describes the Tencent AI Lab submission of the WMT2020 shared task on biomedical translation in four language directions: German<->English, English<->German, Chinese<->English and English<->Chinese.
no code implementations • WMT (EMNLP) 2020 • Longyue Wang, Zhaopeng Tu, Xing Wang, Li Ding, Liang Ding, Shuming Shi
This paper describes the Tencent AI Lab’s submission of the WMT 2020 shared task on chat translation in English-German.
1 code implementation • 20 Jan 2023 • Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Xing Wang, Zhaopeng Tu
This report provides a preliminary evaluation of ChatGPT for machine translation, including translation prompt, multilingual translation, and translation robustness.
no code implementations • 10 Nov 2022 • Jigang Tong, Fanhang Yang, Sen yang, Enzeng Dong, Shengzhi Du, Xing Wang, Xianlin Yi
The cosh-attention module reduces the space and time complexity of the attention operation.
1 code implementation • 17 Oct 2022 • Zhiwei He, Xing Wang, Zhaopeng Tu, Shuming Shi, Rui Wang
Finally, our unconstrained system achieves BLEU scores of 17. 0 and 30. 4 for English to/from Livonian.
1 code implementation • 13 Oct 2022 • Jinhui Ye, Wenxiang Jiao, Xing Wang, Zhaopeng Tu
In this paper, to overcome the limitation, we propose a Prompt based domain text Generation (PGEN) approach to produce the large-scale in-domain spoken language text data.
1 code implementation • COLING 2022 • Junjie Yu, Xing Wang, Jiangjiang Zhao, Chunjie Yang, Wenliang Chen
The approach first classifies the auto-annotated instances into two groups: confident instances and uncertain instances, according to the probabilities predicted by a teacher model.
no code implementations • 4 Aug 2022 • Hanwen Kang, Xing Wang
In this work, we propose a deep-learning-based segmentation method to perform accurate semantic segmentation on fused data from a LiDAR-Camera visual sensor.
2 code implementations • 12 Jul 2022 • Jiashi Li, Xin Xia, Wei Li, Huixia Li, Xing Wang, Xuefeng Xiao, Rui Wang, Min Zheng, Xin Pan
Then, Next Hybrid Strategy (NHS) is designed to stack NCB and NTB in an efficient hybrid paradigm, which boosts performance in various downstream tasks.
Ranked #233 on
Image Classification
on ImageNet
no code implementations • 31 May 2022 • Xing Wang, Yijun Wang
Federated Learning is a rapidly growing area of research and with various benefits and industry applications.
no code implementations • 31 May 2022 • Xing Wang, Yuntian He
We design and implement a temporal convolutional network model to predict sepsis onset.
1 code implementation • 25 May 2022 • Hailong Ma, Xin Xia, Xing Wang, Xuefeng Xiao, Jiashi Li, Min Zheng
Recently, Transformer networks have achieved impressive results on a variety of vision tasks.
no code implementations • 19 May 2022 • Xin Xia, Jiashi Li, Jie Wu, Xing Wang, Xuefeng Xiao, Min Zheng, Rui Wang
We revisit the existing excellent Transformers from the perspective of practical application.
no code implementations • 19 Apr 2022 • Zhuoran Li, Xing Wang, Ling Pan, Lin Zhu, Zhendong Wang, Junlan Feng, Chao Deng, Longbo Huang
A2C-GS consists of three novel components, including a verifier to validate the correctness of a generated network topology, a graph neural network (GNN) to efficiently approximate topology rating, and a DRL actor layer to conduct a topology search.
1 code implementation • 29 Mar 2022 • Wei Li, Xing Wang, Xin Xia, Jie Wu, Xuefeng Xiao, Min Zheng, Shiping Wen
SepViT helps to carry out the information interaction within and among the windows via a depthwise separable self-attention.
no code implementations • ACL 2022 • Wenxuan Wang, Wenxiang Jiao, Yongchang Hao, Xing Wang, Shuming Shi, Zhaopeng Tu, Michael Lyu
In this paper, we present a substantial step in better understanding the SOTA sequence-to-sequence (Seq2Seq) pretraining for neural machine translation~(NMT).
1 code implementation • ACL 2022 • Zhiwei He, Xing Wang, Rui Wang, Shuming Shi, Zhaopeng Tu
By carefully designing experiments, we identify two representative characteristics of the data gap in source: (1) style gap (i. e., translated vs. natural text style) that leads to poor generalization capability; (2) content gap that induces the model to produce hallucination content biased towards the target language.
no code implementations • 8 Dec 2021 • Hanwen Kang, Xing Wang, Chao Chen
It is vital for robots to recognise and localise fruits before the harvesting in natural orchards.
no code implementations • 1 Nov 2021 • Xing Wang, Juan Zhao, Lin Zhu, Xu Zhou, Zhao Li, Junlan Feng, Chao Deng, Yong Zhang
AMF-STGCN extends GCN by (1) jointly modeling the complex spatial-temporal dependencies in mobile networks, (2) applying attention mechanisms to capture various Receptive Fields of heterogeneous base stations, and (3) introducing an extra decoder based on a fully connected deep network to conquer the error propagation challenge with multi-step forecasting.
no code implementations • 27 Oct 2021 • Cheolhei Lee, Xing Wang, Jianguo Wu, Xiaowei Yue
Active learning is a subfield of machine learning that is devised for design and modeling of systems with highly expensive sampling costs.
1 code implementation • ACL 2021 • Wenxiang Jiao, Xing Wang, Zhaopeng Tu, Shuming Shi, Michael R. Lyu, Irwin King
In this work, we propose to improve the sampling procedure by selecting the most informative monolingual sentences to complement the parallel data.
no code implementations • 27 May 2021 • Guoping Huang, Lemao Liu, Xing Wang, Longyue Wang, Huayang Li, Zhaopeng Tu, Chengyan Huang, Shuming Shi
Automatic machine translation is super efficient to produce translations yet their quality is not guaranteed.
no code implementations • 24 Feb 2021 • Xing Wang, Alexander Vinel
In this paper, we benchmark several existing graph neural network (GNN) models on different datasets for link predictions.
no code implementations • 1 Jan 2021 • Xing Wang, Lin Zhu, Juan Zhao, Zhou Xu, Zhao Li, Junlan Feng, Chao Deng
Spatial-temporal data forecasting is of great importance for industries such as telecom network operation and transportation management.
no code implementations • 29 Dec 2020 • Shuyuan Lin, Xing Wang, Guobao Xiao, Yan Yan, Hanzi Wang
In this paper, we propose a novel hierarchical representation via message propagation (HRMP) method for robust model fitting, which simultaneously takes advantages of both the consensus analysis and the preference analysis to estimate the parameters of multiple model instances from data corrupted by outliers, for robust model fitting.
no code implementations • 27 Oct 2020 • Tongtong Li, Xing Wang, Ivan Yotov
In this paper, we focus on investigating the influence on hydrodynamic factors of different coupled computational models describing the interaction between an incompressible fluid and two symmetric elastic or poroelastic structures.
Fluid Dynamics Numerical Analysis Numerical Analysis
1 code implementation • NAACL 2021 • Yongchang Hao, Shilin He, Wenxiang Jiao, Zhaopeng Tu, Michael Lyu, Xing Wang
In addition, experimental results demonstrate that our Multi-Task NAT is complementary to knowledge distillation, the standard knowledge transfer method for NAT.
no code implementations • 18 Oct 2020 • Vipul Gupta, Dhruv Choudhary, Ping Tak Peter Tang, Xiaohan Wei, Xing Wang, Yuzhen Huang, Arun Kejariwal, Kannan Ramchandran, Michael W. Mahoney
This is done by identifying and updating only the most relevant neurons of the neural network for each training sample in the data.
1 code implementation • EMNLP 2020 • Wenxiang Jiao, Xing Wang, Shilin He, Irwin King, Michael R. Lyu, Zhaopeng Tu
First, we train an identification model on the original training data, and use it to distinguish inactive examples and active examples by their sentence-level output probabilities.
no code implementations • 29 Sep 2020 • Xing Wang, Alexander Vinel
Existing exploration strategies in reinforcement learning (RL) often either ignore the history or feedback of search, or are complicated to implement.
no code implementations • 29 Sep 2020 • Xing Wang, Yijun Wang, Bin Weng, Aleksandr Vinel
We have proposed to develop a global hybrid deep learning framework to predict the daily prices in the stock market.
no code implementations • 29 Sep 2020 • Xing Wang, Alexander Vinel
In this work, we propose a novel cross Q-learning algorithm, aim at alleviating the well-known overestimation problem in value-based reinforcement learning methods, particularly in the deep Q-networks where the overestimation is exaggerated by function approximation errors.
no code implementations • 15 May 2020 • Xin Xia, Xuefeng Xiao, Xing Wang, Min Zheng
In this way, PAD-NAS can automatically design the operations for each layer and achieve a trade-off between search space quality and model diversity.
1 code implementation • ACL 2020 • Xinwei Geng, Long-Yue Wang, Xing Wang, Bing Qin, Ting Liu, Zhaopeng Tu
Self-attention networks (SANs) with selective mechanism has produced substantial improvements in various NLP tasks by concentrating on a subset of input words.
no code implementations • 28 Apr 2020 • Shilin He, Xing Wang, Shuming Shi, Michael R. Lyu, Zhaopeng Tu
In this paper, we bridge the gap by assessing the bilingual knowledge learned by NMT models with phrase table -- an interpretable table of bilingual lexicons.
no code implementations • 22 Nov 2019 • Jian Li, Xing Wang, Baosong Yang, Shuming Shi, Michael R. Lyu, Zhaopeng Tu
Starting from this intuition, we propose a novel approach to compose representations learned by different components in neural machine translation (e. g., multi-layer networks or multi-head attention), based on modeling strong interactions among neurons in the representation vectors.
no code implementations • IJCNLP 2019 • Jie Hao, Xing Wang, Shuming Shi, Jinfeng Zhang, Zhaopeng Tu
Current state-of-the-art neural machine translation (NMT) uses a deep multi-head self-attention network with no explicit phrase information.
no code implementations • IJCNLP 2019 • Jie Hao, Xing Wang, Shuming Shi, Jinfeng Zhang, Zhaopeng Tu
Recent studies have shown that a hybrid of self-attention networks (SANs) and recurrent neural networks (RNNs) outperforms both individual architectures, while not much is known about why the hybrid models work.
no code implementations • IJCNLP 2019 • Xing Wang, Zhaopeng Tu, Long-Yue Wang, Shuming Shi
Although self-attention networks (SANs) have advanced the state-of-the-art on various NLP tasks, one criticism of SANs is their ability of encoding positions of input words (Shaw et al., 2018).
no code implementations • IJCNLP 2019 • Long-Yue Wang, Zhaopeng Tu, Xing Wang, Shuming Shi
In this paper, we propose a unified and discourse-aware ZP translation approach for neural MT models.
no code implementations • IJCNLP 2019 • Shilin He, Zhaopeng Tu, Xing Wang, Long-Yue Wang, Michael R. Lyu, Shuming Shi
Although neural machine translation (NMT) has advanced the state-of-the-art on various language pairs, the interpretability of NMT remains unsatisfactory.
no code implementations • ACL 2019 • Xing Wang, Zhaopeng Tu, Long-Yue Wang, Shuming Shi
In this work, we present novel approaches to exploit sentential context for neural machine translation (NMT).
no code implementations • 10 May 2019 • Xing Wang, Jun Wang, Carlotta Domeniconi, Guoxian Yu, Guo-Qiang Xiao, Maozu Guo
To ease this process, we consider diverse clusterings embedded in different subspaces, and analyze the embedding subspaces to shed light into the structure of each clustering.
no code implementations • NAACL 2019 • Jie Hao, Xing Wang, Baosong Yang, Long-Yue Wang, Jinfeng Zhang, Zhaopeng Tu
In addition to the standard recurrent neural network, we introduce a novel attentive recurrent network to leverage the strengths of both attention and recurrent networks.
no code implementations • NAACL 2019 • Jian Li, Baosong Yang, Zi-Yi Dou, Xing Wang, Michael R. Lyu, Zhaopeng Tu
Multi-head attention is appealing for its ability to jointly extract different types of information from multiple representation subspaces.
no code implementations • 15 Feb 2019 • Zi-Yi Dou, Zhaopeng Tu, Xing Wang, Long-Yue Wang, Shuming Shi, Tong Zhang
With the promising progress of deep neural networks, layer aggregation has been used to fuse information across layers in various fields, such as computer vision and machine translation.
no code implementations • 15 Feb 2019 • Baosong Yang, Jian Li, Derek Wong, Lidia S. Chao, Xing Wang, Zhaopeng Tu
Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies.
no code implementations • 26 Dec 2018 • Xinwei Geng, Long-Yue Wang, Xing Wang, Bing Qin, Ting Liu, Zhaopeng Tu
Neural machine translation (NMT) models generally adopt an encoder-decoder architecture for modeling the entire translation process.
no code implementations • EMNLP 2018 • Zi-Yi Dou, Zhaopeng Tu, Xing Wang, Shuming Shi, Tong Zhang
Advanced neural machine translation (NMT) models generally implement encoder and decoder as multiple layers, which allows systems to model complex functions and capture complicated linguistic structures.
no code implementations • 1 Oct 2018 • Xiang Li, Qitian Chen, Xing Wang, Ning Guo, Nan Wu, Quanzheng Li
In this work, we developed a network inference method from incomplete data ("PathInf") , as massive and non-uniformly distributed missing values is a common challenge in practical problems.
no code implementations • EMNLP 2017 • Xing Wang, Zhaopeng Tu, Deyi Xiong, Min Zhang
Otherwise, the NMT decoder generates a word from the vocabulary as the general NMT decoder does.
no code implementations • 17 Oct 2016 • Xing Wang, Zhengdong Lu, Zhaopeng Tu, Hang Li, Deyi Xiong, Min Zhang
Neural Machine Translation (NMT) is a new approach to machine translation that has made great progress in recent years.
no code implementations • 26 Aug 2016 • Xing Wang, Jie Liang
Deep neural networks generally involve some layers with mil- lions of parameters, making them difficult to be deployed and updated on devices with limited resources such as mobile phones and other smart embedded systems.