Fandong Meng (孟凡东)

Personal Information

He is a Research Scientist and Manager at Pattern Recognition Center, WeChat AI, Tencent.

He got his Ph.D. degree at Institute of Computing Technology,
Chinese Academy of Sciences advised by Prof. Qun Liu.

His research focuses on deep learning for natural language processing,
machine translation, and dialogue system.

E-mail: fandongmeng [at] tencent [dot] com

News

Publications

2021

• Chenze Shao, Yang Feng, Jinchao Zhang, Fandong Meng and Jie Zhou. Sequence-Level Training for Non-Autoregressive Neural Machine Translation. To appear in Computational Linguistics. [arxiv]
• Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu and Jie Zhou. Scheduled Sampling Based on Decoding Steps for Neural Machine Translation. In Proceedings of EMNLP 2021. [arxiv]
• Yunlong Liang, Chulun Zhou, Fandong Meng, Jinan Xu, Yufeng Chen, Jinsong Su and Jie Zhou. Towards Making the Most of Dialogue Characteristics for Neural Chat Translation. In Proceedings of EMNLP 2021. [arxiv]
• Shaopeng Lai, Ante Wang, Fandong Meng, Jie Zhou, Yubin Ge, Jiali Zeng, Junfeng Yao, Degen Huang and Jinsong Su. Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings. In Proceedings of EMNLP 2021.
• Mingliang Zhang, Fandong Meng, Yunhai Tong and Jie Zhou. Competence-based Curriculum Learning for Multilingual Machine Translation. In Findings of EMNLP 2021. [arxiv]
• Yunlong Liang, Fandong Meng, Jinchao Zhang, Yufeng Chen, Jinan Xu and Jie Zhou. An Iterative Multi-Knowledge Transfer Network for Aspect-Based Sentiment Analysis. In Findings of EMNLP 2021. [arxiv]
• Duo Zheng, Zipeng Xu, Fandong Meng, Xiaojie Wang, Jiaan Wang and Jie Zhou. Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser. In Findings of EMNLP 2021. [arxiv]
• Xianfeng Zeng, Yijin Liu, Ernan Li, Qiu Ran, Fandong Meng, Peng Li, Jinan Xu, Jie Zhou. WeChat Neural Machine Translation Systems for WMT21. Submitted to WMT 2021 as a system paper. [arxiv]
• Mengqi Miao, Fandong Meng, Yijin Liu, Xiao-Hua Zhou and Jie Zhou. Prevent the Language Model from being Overconfident in Neural Machine Translation. In Proceedings of ACL-IJCNLP 2021. [arxiv]
• Yunlong Liang, Fandong Meng, Yufeng Chen, Jinan Xu and Jie Zhou. Modeling Bilingual Conversational Characteristics for Neural Chat Translation. In Proceedings of ACL-IJCNLP 2021. [arxiv]
• Fusheng Wang, Jianhao Yan, Fandong Meng and Jie Zhou. Selective Knowledge Distillation for Neural Machine Translation. In Proceedings of ACL-IJCNLP 2021. [arxiv]
• Yuanxin Liu, Fandong Meng, Zheng Lin, Weiping Wang and Jie Zhou. Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation. In Proceedings of ACL-IJCNLP 2021. [arxiv]
• Lei Shen, Fangdong Meng, Jinchao Zhang, Yang Feng and Jie Zhou. GTM: A Generative Triple-wise Model for Conversational Question Generation. In Proceedings of ACL-IJCNLP 2021. [arxiv]
• Hui Jiang, Chulun Zhou, Fandong Meng, Biao Zhang, Jie Zhou, Degen Huang, Qingqiang Wu and Jinsong Su. Exploring Dynamic Selection of Branch Expansion Orders for Code Generation. In Proceedings of ACL-IJCNLP 2021. [arxiv]
• Yangyifan Xu, Yijin Liu, Fandong Meng, Jiajun Zhang, Jinan Xu and Jie Zhou. Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation. In Proceedings of ACL-IJCNLP(short) 2021. [arxiv]
• Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu and Jie Zhou. Confidence-Aware Scheduled Sampling for Neural Machine Translation. In Findings of ACL-IJCNLP 2021. [arxiv]
• Ying Zhang, Fandong Meng, Yufeng Chen, Jinan Xu and Jie Zhou. Target-oriented Fine-tuning for Zero-Resource Named Entity Recognition. In Findings of ACL-IJCNLP 2021. [arxiv]
• Feilong Chen, Fandong Meng, Xiuyi Chen, Peng Li and Jie Zhou. Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation. In Findings of ACL-IJCNLP 2021. [paper]
• Feilong Chen, Xiuyi Chen, Fandong Meng, Peng Li and Jie Zhou. GoG: Relation-aware Graph-over-Graph Network for Visual Dialog. In Findings of ACL-IJCNLP 2021. [paper]
• Xiuyi Chen, Feilong Chen, Fandong Meng, Peng Li and Jie Zhou. Unsupervised Knowledge Selection for Dialogue Generation. In Findings of ACL-IJCNLP 2021. [paper]
• Yingxue Zhang, Fandong Meng, Peng Li, Ping Jian and Jie Zhou. Context Tracking Network: Graph-based Context Modeling for Implicit Discourse Relation Recognition. In Proceedings of NAACL (short) 2021. [paper]
• Yijin Liu, Fandong Meng, Jie Zhou, Yufeng Chen and Jinan Xu. Faster Depth-Adaptive Transformers. In Proceedings of AAAI 2021. [arxiv]
• Yunlong Liang, Fandong Meng, Ying Zhang, Yufeng Chen, Jinan Xu and Jie Zhou. Infusing Multi-Source Knowledge with Heterogeneous Graph Neural Network for Emotional Conversation Generation. In Proceedings of AAAI 2021. [arxiv]
• Jianhao Yan, Chenming Wu, Fandong Meng, Jie Zhou. Rethinking the Evaluation of Neural Machine Translation. [arxiv]
• Zipeng Xu, Fandong Meng, Xiaojie Wang, Duo Zheng, Chenxu Lv and Jie Zhou. Modeling Explicit Concerning States for Reinforcement Learning in Visual Dialogue. [arxiv]

2020

• Fandong Meng, Jianhao Yan, Yijin Liu, Yuan Gao, Xianfeng Zeng, Qinsong Zeng, Peng Li, Ming Chen, Jie Zhou, Sifan Liu, Hao Zhou. WeChat Neural Machine Translation Systems for WMT20. In Proceedings of the Fifth Conference on Machine Translation (WMT20), November 19-20. [arxiv] (Our Chinese to English system achieved the highest case-sensitive BLEU score among all submissions.)
• Jianhao Yan, Fandong Meng and Jie Zhou. Multi-Unit Transformers for Neural Machine Translation. In Proceedings of EMNLP 2020, November 16-20. [arxiv]
• Xiuyi Chen, Fandong Meng, Peng Li, Feilong Chen, Shuang Xu, Bo Xu and Jie Zhou. Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation. In Proceedings of EMNLP 2020, November 16-20. [paper]
• Shuhao Gu, Jinchao Zhang, Fandong Meng, Yang Feng, Wanying Xie, Jie Zhou and Dong Yu. Token-level Adaptive Training for Neural Machine Translation. In Proceedings of EMNLP 2020, November 16-20. [arxiv]
• Lin Qiao, Jianhao Yan, Fandong Meng, Zhendong Yang and Jie Zhou. A Sentiment-Controllable Topic-to-Essay Generator with Topic Knowledge Graph. In Findings of EMNLP 2020, November 16-20. [arxiv]
• Huan Lin, Fandong Meng, Jinsong Su, Yongjing Yin, Zhengyuan Yang, Yubin Ge, Jie Zhou and Jiebo Luo. Dynamic Context-guided Capsule Network for Multimodal Machine Translation. In Proceedings of ACM MM 2020, October. [arxiv]
• Yongjing Yin, Fandong Meng, Jinsong Su, Chulun Zhou, Zhengyuan Yang, Jie Zhou and Jiebo Luo. A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation. In Proceedings of ACL 2020 , Seattle, USA, July. [paper]
• Xianggen Liu, Lili Mou, Fandong Meng, Hao Zhou, Jie Zhou and Sen Song. Unsupervised Paraphrasing by Simulated Annealing. In Proceedings of ACL 2020 , Seattle, USA, July. [paper]
• Fandong Meng, Jinchao Zhang, Yang Liu and Jie Zhou. Multi-Zone Unit for Recurrent Neural Networks. In Proceedings of AAAI 2020 , New York, USA, February 7-12. [arxiv]
• Yongjing Yin, Fandong Meng, Jinsong Su, Yubin Ge, Linfeng Song, Jie Zhou and Jiebo Luo. Enhancing Pointer Network for Sentence Ordering with Pairwise Ordering Predictions. In Proceedings of AAAI 2020 , New York, USA, February 7-12. [paper]
• Feilong Chen, Fandong Meng, Jiaming Xu, Peng Li, Bo Xu and Jie Zhou. DMRM: A Dual-channel Multi-hop Reasoning Model for Visual Dialog. In Proceedings of AAAI 2020 , New York, USA, February 7-12. [arxiv]
• Chenze Shao, Jinchao Zhang, Yang Feng, Fandong Meng and Jie Zhou. Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation. In Proceedings of AAAI 2020, New York, USA, February 7-12. [arxiv]
• Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu and Jie Zhou. Depth-Adaptive Graph Recurrent Network for Text Classification. [arxiv]
• Yunlong Liang, Fandong Meng, Jinchao Zhang, Jinan Xu, Yufeng Chen and Jie Zhou. A Dependency Syntactic Knowledge Augmented Interactive Architecture for End-to-End Aspect-based Sentiment Analysis. [arxiv]
• Zeyang Lei, Zekang Li, Jinchao Zhang, Fandong Meng, Yang Feng, Yujiu Yang, Cheng Niu, Jie Zhou. Towards Multimodal Response Generation with Exemplar Augmentation and Curriculum Optimization. [arxiv]
• Yong Shan, Zekang Li, Jinchao Zhang, Fandong Meng, Yang Feng, Cheng Niu, Jie Zhou. A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking. [arxiv]

2019

• Yijin Liu, Fandong Meng, Jinchao Zhang, Jie Zhou, Yufeng Chen and Jinan Xu. CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding. In Proceedings of EMNLP 2019, Hong Kong, China, November 3–7. [paper] [arxiv] [code]
• Yunlong Liang, Fandong Meng, Jinchao Zhang, Jinan Xu, Yufeng Chen and Jie Zhou. A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysis. In Proceedings of EMNLP 2019, Hong Kong, China, November 3–7. [paper] [arxiv] [code]
• Zhengxin Yang, Jinchao Zhang, Fandong Meng, Shuhao Gu, Yang Feng and Jie Zhou. Enhancing Context Modeling with a Query-Guided Capsule Network for Document-level NMT. In Proceedings of EMNLP 2019 , Hong Kong, China, November 3–7. [paper] [arxiv]
• Yijin Liu, Fandong Meng, Jinchao Zhang, Jinan Xu, Yufeng Chen and Jie Zhou. GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling. In Proceedings of ACL 2019, Florence, Italy, July 28-August 2. [arxiv] [paper] [code]
• Zekang Li, Cheng Niu, Fandong Meng, Yang Feng, Qian Li and Jie Zhou. Incremental Transformer with Deliberation Decoder for Document Grounded Conversations. In Proceedings of ACL 2019, Florence, Italy, July 28-August 2. [arxiv] [paper] [code]
• Wen Zhang, Yang Feng, Fandong Meng, Di You and Qun Liu. Bridging the Gap between Training and Inference for Neural Machine Translation. In Proceedings of ACL 2019, Florence, Italy, July 28-August 2. (Best Long Paper Award) [arxiv] [paper] [code]
• Chenze Shao, Yang Feng, Jinchao Zhang, Fandong Meng, Xilin Chen and Jie Zhou. Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation. In Proceedings of ACL 2019, Florence, Italy, July 28-August 2. [arxiv] [paper] [code]
• Fandong Meng and Jinchao Zhang. DTMT: A Novel Deep Transition Architecture for Neural Machine Translation. In Proceedings of AAAI 2019, Hawaii, USA, January. [paper] [arxiv] [code]
• Yingxue Zhang, Ping Jian, Ruiying Geng, Yuansheng Song and Fandong Meng. Ranking Like Human: Global-View Matching via Reinforcement Learning for Answer Selection. In Proceedings of IALP 2019, Shanghai, China, November. [paper]
• Yingxue Zhang, Ping Jian, Fandong Meng, Ruiying Geng, Wei Cheng and Jie Zhou. Semantic Graph Convolutional Network for Implicit Discourse Relation Classification. [arxiv]
• Yong Shan, Yang Feng, Jinchao Zhang, Fandong Meng and Wen Zhang. Improving Bidirectional Decoding with Dynamic Target Semantics in Neural Machine Translation. [arxiv]

2018

• Fandong Meng, Zhaopeng Tu, Yong Cheng, Haiyang Wu, Junjie Zhai, Yuekui Yang, and Di Wang. Neural Machine Translation with Key-Value Memory-Augmented Attention. In Proceedings of IJCAI 2018, Stockholm, Sweden, July. [paper]
• Yong Cheng, Zhaopeng Tu, Fandong Meng, Junjie Zhai, and Yang Liu. Towards Robust Neural Machine Translation. In Proceedings of ACL 2018, Melbourne, Australia, July. [paper]
• Baosong Yang, Zhaopeng Tu, Derek F. Wong, Fandong Meng, Lidia S. Chao and Tong Zhang. Modeling Localness for Self-Attention Networks. In Proceedings of EMNLP 2018, Brussels, Belgium, October.

2016

• Fandong Meng, Zhengdong Lu, Hang Li, and Qun Liu. Interactive Attention for Neural Machine Translation. In Proceedings of COLING 2016, Japan, December. [paper] [arxiv]
• Fandong Meng, Zhengdong Lu, Zhaopeng Tu, Hang Li, and Qun Liu. A Deep Memory-based Architecture for Sequence-to-Sequence Learning. In Proceedings of ICLR-Workshop 2016, Canada, May. [paper] [arxiv]
• Deyi Xiong, Fandong Meng, and Qun Liu. Topic-based Term Translation Models for Statistical Machine Translation. In Artificial Intelligence, 232:54-75, March 1, 2016. [paper]
• Yaohua Tang, Fandong Meng, Zhengdong Lu, Hang Li, Philip L. H. Yu. Neural Machine Translation with External Phrase Memory. In CoRR abs/1606.01792.(2016) [paper]
• Jinchao Zhang, Fandong Meng, Mingxuan Wang, Daqi Zheng, Wenbin Jiang, Qun Liu. Is Local Window Essential for Neural Network Based Chinese Word Segmentation? In CCL 2016, 450-457. [paper]
• Qingsong Ma, Fandong Meng, Daqi Zheng, Mingxuan Wang, Yvette Graham, Wenbin Jiang, Qun Liu. MaxSD: A Neural Machine Translation Evaluation Metric Optimized by Maximizing Similarity Distance. In NLPCC/ICCPOL 2016, 153-161. [paper]

2011~2015

• Fandong Meng, Zhengdong Lu, Mingxuan Wang, Hang Li, Wenbin Jiang, and Qun Liu. Encoding Source Language with Convolutional Neural Network for Machine Translation. In Proceedings of ACL 2015, Beijing, China, July. [paper] [arxiv]
• Fandong Meng, Deyi Xiong, Wenbin Jiang, and Qun Liu. Modeling Term Translation for Document-informed Machine Translation. In Proceedings of EMNLP 2014, Doha, Qatar, October. [paper]
• Hongshen Chen, Jun Xie, Fandong Meng, Wenbin Jiang, and Qun Liu. A Dependency Edge-based Transfer Model for Statistical Machine Translation. In Proceedings of COLING 2014, Dublin, Ireland, August. [paper]
• Fandong Meng, Jun Xie, Linfeng Song, Yajuan lv and Qun Liu. Translation with Source Constituency and Dependency Trees. In Proceedings of EMNLP 2013, Seattle, Washington, USA, October. [paper]
• Fandong Meng, Wenbin Jiang, Hao Xiong and Qun Liu. Discriminative Boosting from Dictionary and Raw Text -- A Novel Approach to Build A Chinese Word Segmenter. In Proceedings of COLING 2012, IIT Bombay, Mumbai, India, December. [paper]
• Fandong Meng, Jin'an Xu, Wenbin Jiang and Qun Liu. A Method of Merging Corpora in Different Annotation Standards: An Application on Statistics Chinese Lexical Analysis. In Journal of Chinese Information Processing 26(2):3-7. [paper]
• Fandong Meng, Hao Xiong and Qun Liu. ICT: A Translation based Method for Cross-lingual Textual Entailment. In Proceedings of SemEval 2012, Canada. [paper]
• Wenbin Jiang, Fandong Meng, Qun Liu and Yajuan Lv. Iterative Annotation Transformation with Predict-Self Reestimation for Chinese Word Segmentation. In Proceedings of EMNLP 2012, Jeju, Korea, July. [paper]
• Hao Xiong, Linfeng Song, Fandong Meng, Yang Liu, Qun Liu and Yajuan Lv. ETS: An Error Tolerable System for Coreference Resolution. In Proceedings of CoNLL 2011, America. [paper]
• Hao Xiong, Linfeng Song, Fandong Meng, Yajuan Lv and Qun Liu. The ICT's Patent MT System Description for NTCIR-9. In Proceedings of NTCIR9 2011, Tokyo, Japan. [paper]

Professional Services

• Standing Reviewer: TACL (2021-)
• Meta-Reviewer: AAAI 2022 (Senior PC Member)
• PC Member & Reviewer: ACL (2014, 2017-2021), EMNLP (2018, 2020, 2021), NAACL (2016, 2018, 2021), AAAI (2020, 2021), IJCAI (2019), COLING (2018)

Honours

• Champion of WMT21 news translation task on English->Chinese, English->Japanese, Japanese->English, and English->German (among constrained systems), 2021
• Champion of WMT20 news translation task on Chinese->English, 2020
• ACL Best Long Paper Award, 2019
• Director Scholarship for Graduate Student, 2015
• UCAS Outstanding Student Award, 2013 and 2014
• Outstanding Winner (world 1/14) of COMAP's Mathematical Contest in Modeling (MCM/ICM), 2010
• First Prize Winner of National Mathematic Contest In Modeling, 2009