Yu Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yu Zhang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jiajun Chen
Nanjing University
6 shared publications - Shujian Huang
National Key Laboratory for Novel Software Technology Nanjing University
6 shared publications - Hao Yang
National University of Defense Technology
4 shared publications - Shimin Tao
Huawei
4 shared publications Xiang Geng
National Key Laboratory for Novel Software Technology Nanjing University Nanjing China
4 shared publications- Xiang Geng
National Key Laboratory for Novel Software Technology Nanjing University Nanjing China
2 shared publications
Latest Publications
- Open Access
Unify word-level and span-level tasks: NJUNLP's Participation for the WMT2023 Quality Estimation Shared Task
We introduce the submissions of the NJUNLP team to the WMT 2023 Quality Estimation (QE) shared task. Our team submitted predictions for the English-German language pair on all two sub-tasks: (i) sentence- and word-level quality prediction; and (ii) fine-grained error span detection. This year, we further explore pseudo data methods for QE based on NJUQE framework (https://github.com/NJUNLP/njuqe). We generate pseudo MQM data using parallel data from the WMT translation task. We pre-train the XLMR large model on pseudo QE data, then fine-tune it on real QE data. At both stages, we jointly learn sentence-level scores and word-level tags. Empirically, we conduct experiments to find the key hyper-parameters that improve the performance. Technically, we propose a simple method that covert the word-level outputs to fine-grained error span results. Overall, our models achieved the best results in English-German for both word-level and fine-grained error span detection sub-tasks by a considerable margin.
Open AccessUnify word-level and span-level tasks: NJUNLP's Participation for the WMT2023 Quality Estimation Shared Task
We introduce the submissions of the NJUNLP team to the WMT 2023 Quality Estimation (QE) shared task. Our team submitted predictions for the English-German language pair on all two sub-tasks: (i) sentence- and word-level quality prediction; and (ii) fine-grained error span detection. This year, we further explore pseudo data methods for QE based on NJUQE framework (https://github.com/NJUNLP/njuqe). We generate pseudo MQM data using parallel data from the WMT translation task. We pre-train the XLMR large model on pseudo QE data, then fine-tune it on real QE data. At both stages, we jointly learn sentence-level scores and word-level tags. Empirically, we conduct experiments to find the key hyper-parameters that improve the performance. Technically, we propose a simple method that covert the word-level outputs to fine-grained error span results. Overall, our models achieved the best results in English-German for both word-level and fine-grained error span detection sub-tasks by a considerable margin.
- 1 November 2023
- Published by Springer Nature
- p. 50-56
NJUNLP’s Submission for CCMT 2023 Quality Estimation Task
- 1 November 2023
- Published by Springer Nature
- p. 50-56
NJUNLP’s Submission for CCMT 2023 Quality Estimation Task
- Open Access
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (11) , 12827-12835
Denoising Pre-training for Machine Translation Quality Estimation with Curriculum Learning
Quality estimation (QE) aims to assess the quality of machine translations when reference translations are unavailable. QE plays a crucial role in many real-world applications of machine translation. Because labeled QE data are usually limited in scale, recent research, such as DirectQE, pre-trains QE models with pseudo QE data and obtains remarkable performance. However, there tends to be inevitable noise in the pseudo data, hindering models from learning QE accurately. Our study shows that the noise mainly comes from the differences between pseudo and real translation outputs. To handle this problem, we propose CLQE, a denoising pre-training framework for QE based on curriculum learning. More specifically, we propose to measure the degree of noise in the pseudo QE data with some metrics based on statistical or distributional features. With the guidance of these metrics, CLQE gradually pre-trains the QE model using data from cleaner to noisier. Experiments on various benchmarks reveal that CLQE outperforms DirectQE and other strong baselines. We also show that with our framework, pre-training converges faster than directly using the pseudo data. We make our CLQE code available (https://github.com/NJUNLP/njuqe).
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (11) , 12827-12835
Open AccessDenoising Pre-training for Machine Translation Quality Estimation with Curriculum Learning
Quality estimation (QE) aims to assess the quality of machine translations when reference translations are unavailable. QE plays a crucial role in many real-world applications of machine translation. Because labeled QE data are usually limited in scale, recent research, such as DirectQE, pre-trains QE models with pseudo QE data and obtains remarkable performance. However, there tends to be inevitable noise in the pseudo data, hindering models from learning QE accurately. Our study shows that the noise mainly comes from the differences between pseudo and real translation outputs. To handle this problem, we propose CLQE, a denoising pre-training framework for QE based on curriculum learning. More specifically, we propose to measure the degree of noise in the pseudo QE data with some metrics based on statistical or distributional features. With the guidance of these metrics, CLQE gradually pre-trains the QE model using data from cleaner to noisier. Experiments on various benchmarks reveal that CLQE outperforms DirectQE and other strong baselines. We also show that with our framework, pre-training converges faster than directly using the pseudo data. We make our CLQE code available (https://github.com/NJUNLP/njuqe).
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 829-834
Unify Word-level and Span-level Tasks: NJUNLP’s Participation for the WMT2023 Quality Estimation Shared Task
Xiang Geng, Zhejian Lai, Yu Zhang, Shimin Tao, Hao Yang, Jiajun Chen, Shujian Huang. Proceedings of the Eighth Conference on Machine Translation. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 829-834
Open AccessUnify Word-level and Span-level Tasks: NJUNLP’s Participation for the WMT2023 Quality Estimation Shared Task
Xiang Geng, Zhejian Lai, Yu Zhang, Shimin Tao, Hao Yang, Jiajun Chen, Shujian Huang. Proceedings of the Eighth Conference on Machine Translation. 2023.
- 9 December 2022
- Published by Springer Nature
- p. 143-150
NJUNLP’s Submission for CCMT 2022 Quality Estimation Task
- 9 December 2022
- Published by Springer Nature
- p. 143-150
NJUNLP’s Submission for CCMT 2022 Quality Estimation Task
- Open Access
- 1 January 2022
- Published by Association for Computational Linguistics (ACL)
- p. 615-620
NJUNLP’s Participation for the WMT2022 Quality Estimation Shared Task
Xiang Geng, Yu Zhang, Shujian Huang, Shimin Tao, Hao Yang, Jiajun Chen. Proceedings of the Seventh Conference on Machine Translation (WMT). 2022.
- 1 January 2022
- Published by Association for Computational Linguistics (ACL)
- p. 615-620
Open AccessNJUNLP’s Participation for the WMT2022 Quality Estimation Shared Task
Xiang Geng, Yu Zhang, Shujian Huang, Shimin Tao, Hao Yang, Jiajun Chen. Proceedings of the Seventh Conference on Machine Translation (WMT). 2022.