Yu Wan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yu Wan has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Derek Fai Wong
University of Macau
5 shared publications - Baosong Yang
Tongyi Lab Group Alibaba
4 shared publications Jun Xie
DAMO Academy Alibaba Group
4 shared publications- Wenqiang Lei
College of Computer Science, Sichuan University, Chengdu, China
4 shared publications - Dayiheng Liu
Qwen Team AI Institute 8x Efficiency Alibaba Group 3 UW-Madison 4 UIUC 5 Mila Quebec
3 shared publications Derek F. Wong
CT Lab University of Macau
3 shared publications
Latest Publications
- Open Access
Alibaba-Translate China's Submission for WMT 2022 Quality Estimation Shared Task
In this paper, we present our submission to the sentence-level MQM benchmark at Quality Estimation Shared Task, named UniTE (Unified Translation Evaluation). Specifically, our systems employ the framework of UniTE, which combined three types of input formats during training with a pre-trained language model. First, we apply the pseudo-labeled data examples for the continuously pre-training phase. Notably, to reduce the gap between pre-training and fine-tuning, we use data pruning and a ranking-based score normalization strategy. For the fine-tuning phase, we use both Direct Assessment (DA) and Multidimensional Quality Metrics (MQM) data from past years' WMT competitions. Finally, we collect the source-only evaluation results, and ensemble the predictions generated by two UniTE models, whose backbones are XLM-R and InfoXLM, respectively. Results show that our models reach 1st overall ranking in the Multilingual and English-Russian settings, and 2nd overall ranking in English-German and Chinese-English settings, showing relatively strong performances in this year's quality estimation competition.
Open AccessAlibaba-Translate China's Submission for WMT 2022 Quality Estimation Shared Task
In this paper, we present our submission to the sentence-level MQM benchmark at Quality Estimation Shared Task, named UniTE (Unified Translation Evaluation). Specifically, our systems employ the framework of UniTE, which combined three types of input formats during training with a pre-trained language model. First, we apply the pseudo-labeled data examples for the continuously pre-training phase. Notably, to reduce the gap between pre-training and fine-tuning, we use data pruning and a ranking-based score normalization strategy. For the fine-tuning phase, we use both Direct Assessment (DA) and Multidimensional Quality Metrics (MQM) data from past years' WMT competitions. Finally, we collect the source-only evaluation results, and ensemble the predictions generated by two UniTE models, whose backbones are XLM-R and InfoXLM, respectively. Results show that our models reach 1st overall ranking in the Multilingual and English-Russian settings, and 2nd overall ranking in English-German and Chinese-English settings, showing relatively strong performances in this year's quality estimation competition.
- Open Access
Alibaba-Translate China's Submission for WMT 2022 Metrics Shared Task
In this report, we present our submission to the WMT 2022 Metrics Shared Task. We build our system based on the core idea of UNITE (Unified Translation Evaluation), which unifies source-only, reference-only, and source-reference-combined evaluation scenarios into one single model. Specifically, during the model pre-training phase, we first apply the pseudo-labeled data examples to continuously pre-train UNITE. Notably, to reduce the gap between pre-training and fine-tuning, we use data cropping and a ranking-based score normalization strategy. During the fine-tuning phase, we use both Direct Assessment (DA) and Multidimensional Quality Metrics (MQM) data from past years' WMT competitions. Specially, we collect the results from models with different pre-trained language model backbones, and use different ensembling strategies for involved translation directions.
Open AccessAlibaba-Translate China's Submission for WMT 2022 Metrics Shared Task
In this report, we present our submission to the WMT 2022 Metrics Shared Task. We build our system based on the core idea of UNITE (Unified Translation Evaluation), which unifies source-only, reference-only, and source-reference-combined evaluation scenarios into one single model. Specifically, during the model pre-training phase, we first apply the pseudo-labeled data examples to continuously pre-train UNITE. Notably, to reduce the gap between pre-training and fine-tuning, we use data cropping and a ranking-based score normalization strategy. During the fine-tuning phase, we use both Direct Assessment (DA) and Multidimensional Quality Metrics (MQM) data from past years' WMT competitions. Specially, we collect the results from models with different pre-trained language model backbones, and use different ensembling strategies for involved translation directions.
- Open Access
Towards Fine-Grained Information: Identifying the Type and Location of Translation Errors
Fine-grained information on translation errors is helpful for the translation evaluation community. Existing approaches can not synchronously consider error position and type, failing to integrate the error information of both. In this paper, we propose Fine-Grained Translation Error Detection (FG-TED) task, aiming at identifying both the position and the type of translation errors on given source-hypothesis sentence pairs. Besides, we build an FG-TED model to predict the \textbf{addition} and \textbf{omission} errors -- two typical translation accuracy errors. First, we use a word-level classification paradigm to form our model and use the shortcut learning reduction to relieve the influence of monolingual features. Besides, we construct synthetic datasets for model training, and relieve the disagreement of data labeling in authoritative datasets, making the experimental benchmark concordant. Experiments show that our model can identify both error type and position concurrently, and gives state-of-the-art results on the restored dataset. Our model also delivers more reliable predictions on low-resource and transfer scenarios than existing baselines. The related datasets and the source code will be released in the future.
Open AccessTowards Fine-Grained Information: Identifying the Type and Location of Translation Errors
Fine-grained information on translation errors is helpful for the translation evaluation community. Existing approaches can not synchronously consider error position and type, failing to integrate the error information of both. In this paper, we propose Fine-Grained Translation Error Detection (FG-TED) task, aiming at identifying both the position and the type of translation errors on given source-hypothesis sentence pairs. Besides, we build an FG-TED model to predict the \textbf{addition} and \textbf{omission} errors -- two typical translation accuracy errors. First, we use a word-level classification paradigm to form our model and use the shortcut learning reduction to relieve the influence of monolingual features. Besides, we construct synthetic datasets for model training, and relieve the disagreement of data labeling in authoritative datasets, making the experimental benchmark concordant. Experiments show that our model can identify both error type and position concurrently, and gives state-of-the-art results on the restored dataset. Our model also delivers more reliable predictions on low-resource and transfer scenarios than existing baselines. The related datasets and the source code will be released in the future.
- 29 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1385-1390
Flux-weakening Control of PMSM Based on Model Predictive Control
In this study, an effective flux-weakening control for permanent magnet synchronous motor (PMSM) is proposed, which combines model predictive control (MPC) with vector control. On the one hand, in order to achieve full-speed domain control, the optimal working point of the motor running is tracked and the reference current is calculated according to the feedback information in the speed control loop. On the other hand, MPC replaces the three PI controllers of the speed loop and the current loop in the traditional vector control, which not only does not need to set the PI parameters, but also improves the rapidness and accuracy of the speed control system. The results show that, compared with traditional vector control, the proposed control method has a great dynamic response and disturbance rejection performance in the full-speed domain.
- 29 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1385-1390
Flux-weakening Control of PMSM Based on Model Predictive Control
In this study, an effective flux-weakening control for permanent magnet synchronous motor (PMSM) is proposed, which combines model predictive control (MPC) with vector control. On the one hand, in order to achieve full-speed domain control, the optimal working point of the motor running is tracked and the reference current is calculated according to the feedback information in the speed control loop. On the other hand, MPC replaces the three PI controllers of the speed loop and the current loop in the traditional vector control, which not only does not need to set the PI parameters, but also improves the rapidness and accuracy of the speed control system. The results show that, compared with traditional vector control, the proposed control method has a great dynamic response and disturbance rejection performance in the full-speed domain.
- 10 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 31 (23299290) , 439-447
Towards Energy-Preserving Natural Language Understanding With Spiking Neural Networks
Artificial neural networks have shown promising results in a variety of natural language understanding (NLU) tasks. Despite their successes, conventional neural-based NLU models are criticized for high energy consumption, making them laborious to be widely applied in low-power electronics, such as smartphones and intelligent terminals. In this paper, we introduce a potential direction to alleviate this bottleneck by proposing a spiking encoder. The core of our model is bi-directional spiking neural network (SNN) which transforms numeric values into discrete spiking signals and replaces massive multiplications with much cheaper additive operations. We examine our model on sentiment classification and machine translation tasks. Experimental results reveal that our model achieves comparable classification and translation accuracy to advanced Transformer baseline, whereas significantly reduces the required computational energy to 0.82%.
- 10 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 31 (23299290) , 439-447
Towards Energy-Preserving Natural Language Understanding With Spiking Neural Networks
Artificial neural networks have shown promising results in a variety of natural language understanding (NLU) tasks. Despite their successes, conventional neural-based NLU models are criticized for high energy consumption, making them laborious to be widely applied in low-power electronics, such as smartphones and intelligent terminals. In this paper, we introduce a potential direction to alleviate this bottleneck by proposing a spiking encoder. The core of our model is bi-directional spiking neural network (SNN) which transforms numeric values into discrete spiking signals and replaces massive multiplications with much cheaper additive operations. We examine our model on sentiment classification and machine translation tasks. Experimental results reveal that our model achieves comparable classification and translation accuracy to advanced Transformer baseline, whereas significantly reduces the required computational energy to 0.82%.
- Open Access
- 9 June 2022
- Published by MIT Press in Computational Linguistics
- Vol. 48 (2) , 321-342
Challenges of Neural Machine Translation for Short Texts
Short texts (STs) present in a variety of scenarios, including query, dialog, and entity names. Most of the exciting studies in neural machine translation (NMT) are focused on tackling open problems concerning long sentences rather than short ones. The intuition behind is that, with respect to human learning and processing, short sequences are generally regarded as easy examples. In this article, we first dispel this speculation via conducting preliminary experiments, showing that the conventional state-of-the-art NMT approach, namely, Transformer (Vaswani et al. 2017), still suffers from over-translation and mistranslation errors over STs. After empirically investigating the rationale behind this, we summarize two challenges in NMT for STs associated with translation error types above, respectively: (1) the imbalanced length distribution in training set intensifies model inference calibration over STs, leading to more over-translation cases on STs; and (2) the lack of contextual information forces NMT to have higher data uncertainty on short sentences, and thus NMT model is troubled by considerable mistranslation errors. Some existing approaches, like balancing data distribution for training (e.g., data upsampling) and complementing contextual information (e.g., introducing translation memory) can alleviate the translation issues in NMT for STs. We encourage researchers to investigate other challenges in NMT for STs, thus reducing ST translation errors and enhancing translation quality.
- 9 June 2022
- Published by MIT Press in Computational Linguistics
- Vol. 48 (2) , 321-342
Open AccessChallenges of Neural Machine Translation for Short Texts
Short texts (STs) present in a variety of scenarios, including query, dialog, and entity names. Most of the exciting studies in neural machine translation (NMT) are focused on tackling open problems concerning long sentences rather than short ones. The intuition behind is that, with respect to human learning and processing, short sequences are generally regarded as easy examples. In this article, we first dispel this speculation via conducting preliminary experiments, showing that the conventional state-of-the-art NMT approach, namely, Transformer (Vaswani et al. 2017), still suffers from over-translation and mistranslation errors over STs. After empirically investigating the rationale behind this, we summarize two challenges in NMT for STs associated with translation error types above, respectively: (1) the imbalanced length distribution in training set intensifies model inference calibration over STs, leading to more over-translation cases on STs; and (2) the lack of contextual information forces NMT to have higher data uncertainty on short sentences, and thus NMT model is troubled by considerable mistranslation errors. Some existing approaches, like balancing data distribution for training (e.g., data upsampling) and complementing contextual information (e.g., introducing translation memory) can alleviate the translation issues in NMT for STs. We encourage researchers to investigate other challenges in NMT for STs, thus reducing ST translation errors and enhancing translation quality.
- Open Access
- 1 January 2022
- Published by Association for Computational Linguistics (ACL)
- p. 597-605
Alibaba-Translate China’s Submission for WMT 2022 Quality Estimation Shared Task
Keqin Bao, Yu Wan, Dayiheng Liu, Baosong Yang, Wenqiang Lei, Xiangnan He, Derek F. Wong, Jun Xie. Proceedings of the Seventh Conference on Machine Translation (WMT). 2022.
- 1 January 2022
- Published by Association for Computational Linguistics (ACL)
- p. 597-605
Open AccessAlibaba-Translate China’s Submission for WMT 2022 Quality Estimation Shared Task
Keqin Bao, Yu Wan, Dayiheng Liu, Baosong Yang, Wenqiang Lei, Xiangnan He, Derek F. Wong, Jun Xie. Proceedings of the Seventh Conference on Machine Translation (WMT). 2022.
- Open Access
- 3 April 2020
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 34 (05) , 9130-9137
Unsupervised Neural Dialect Translation with Commonality and Diversity Modeling
As a special machine translation task, dialect translation has two main characteristics: 1) lack of parallel training corpus; and 2) possessing similar grammar between two sides of the translation. In this paper, we investigate how to exploit the commonality and diversity between dialects thus to build unsupervised translation models merely accessing to monolingual data. Specifically, we leverage pivot-private embedding, layer coordination, as well as parameter sharing to sufficiently model commonality and diversity among source and target, ranging from lexical, through syntactic, to semantic levels. In order to examine the effectiveness of the proposed models, we collect 20 million monolingual corpus for each of Mandarin and Cantonese, which are official language and the most widely used dialect in China. Experimental results reveal that our methods outperform rule-based simplified and traditional Chinese conversion and conventional unsupervised translation models over 12 BLEU scores.
- 3 April 2020
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 34 (05) , 9130-9137
Open AccessUnsupervised Neural Dialect Translation with Commonality and Diversity Modeling
As a special machine translation task, dialect translation has two main characteristics: 1) lack of parallel training corpus; and 2) possessing similar grammar between two sides of the translation. In this paper, we investigate how to exploit the commonality and diversity between dialects thus to build unsupervised translation models merely accessing to monolingual data. Specifically, we leverage pivot-private embedding, layer coordination, as well as parameter sharing to sufficiently model commonality and diversity among source and target, ranging from lexical, through syntactic, to semantic levels. In order to examine the effectiveness of the proposed models, we collect 20 million monolingual corpus for each of Mandarin and Cantonese, which are official language and the most widely used dialect in China. Experimental results reveal that our methods outperform rule-based simplified and traditional Chinese conversion and conventional unsupervised translation models over 12 BLEU scores.
- Open Access
- 1 January 2020
- Published by Association for Computational Linguistics (ACL)
- p. 6934-6944
Uncertainty-Aware Curriculum Learning for Neural Machine Translation
Yikai Zhou, Baosong Yang, Derek F. Wong, Yu Wan, Lidia S. Chao. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.
- 1 January 2020
- Published by Association for Computational Linguistics (ACL)
- p. 6934-6944
Open AccessUncertainty-Aware Curriculum Learning for Neural Machine Translation
Yikai Zhou, Baosong Yang, Derek F. Wong, Yu Wan, Lidia S. Chao. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.
- 3 April 2018
- Published by Springer Nature in Soft Computing
- Vol. 22 (21) , 6967-6979
Constructing and validating word similarity datasets by integrating methods from psychology, brain science and computational linguistics
- 3 April 2018
- Published by Springer Nature in Soft Computing
- Vol. 22 (21) , 6967-6979
Constructing and validating word similarity datasets by integrating methods from psychology, brain science and computational linguistics