Xiubo Geng is a Principle Applied Scientist in Microsoft STCA (Software Technology Center Asia). Her research interest includes dense retrieval, large-scale model pre-training, interpretable reasoning in NLP, question answering, semantic parsing, cross-lingual KBQA, dialogue generation etc. She received her B.E. degree in Computer Science from University of Science and Technology of China, and her PhD degree from Institute of Computing Technology, Chinese Academy of Sciences. She has published a dozen of papers in top conferences including ACL, ICLR, SIGIR, EMNLP, WWW, NeurIPS, IJCAI, NAACL etc.

Publications

2023

• Tao Shen, Xiubo Geng, Chongyang Tao, Can Xu, Guodong Long, Kai Zhang, Daxin Jiang. UnifieR: A Unified Retriever for Large-Scale Retrieval. KDD 2023.
• Chongyang Tao, Jiazhan Feng, Tao Shen, Chang Liu, Juntao Li, Xiubo Geng and Daxin Jiang. CORE: Cooperative Training of Retriever-Reranker for Effective Dialogue Response Selection. ACL 2023.
• Zhen Li, Chongyang Tao, Jiazhan Feng, Tao Shen, Dongyan Zhao, Xiubo Geng and Daxin Jiang. FAA: Fine-grained Attention Alignement for Cascade Document Ranking. ACL 2023.
• Yucheng Zhou, Tao Shen, Xiubo Geng, Chongyang Tao, Can Xu, Guodong Long, Binxing Jiao and Daxin Jiang. Towards Robust Ranker for Text Retrieval. ACL 2023 Findings.
• Meng Cao, Fangyun Wei, Can Xu, Xiubo Geng, Long Chen, Can Zhang, Yuexian Zou, Tao Shen, Daxin Jiang. Iterative Proposal Refinement for Weakly-Supervised Video Grounding. CVPR 2023
• Tao Shen, Xiubo Geng, Chongyang Tao, Can Xu, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang. LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval. ICLR 2023.
• Yufei Wang, Jiayi Zheng, Can Xu, Xiubo Geng, Tao Shen, Chongyang Tao, Daxin Jiang. KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP. ICLR 2023.
• ZeFeng Cai, Chongyang Tao, Tao Shen, Can Xu, Xiubo Geng, Xin Alex Lin, Liang He, Daxin Jiang. HypeR: Multitask Hyper-Prompted Training Enables Large-Scale Retrieval Generalization. ICLR 2023.
• Kai Zhang, Chongyang Tao, Tao Shen, Can Xu, Xiubo Geng, Binxing Jiao, Daxin Jiang. LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval. WWW 2023.

2022

• Qian Liu, Xiubo Geng, Yu Wang, Erik Cambria, Daxin Jiang. Disentangled Retrieval and Reasoning for Implicit Question Answering. The IEEE Transactions on Neural Networks and Learning System (TNNLS).
• Qian Liu, Rui Mao, Xiubo Geng, Erik Cambria. Semantic Matching in Machine Reading Comprehension: An Empirical Study. Information Processing and Management.
• Qiyu Wu, Chongyang Tao, Tao Shen, Can Xu, Xiubo Geng and Daxin Jiang. Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings. EMNLP 2022.
• Tao Shen, Xiubo Geng, Daxin Jiang. Social Norms-Grounded Machine Ethics in Complex Narrative Situation. COLING 2022.
• Hao Huang, Xiubo Geng, Guodong Long, Daxin Jiang. Understand before Answer: Improve Temporal Reading Comprehension via Precise Question Understanding. NAACL 2022.
• Qingfeng Sun, Can Xu, Huang Hu, Yujing Wang, Jian Miao, Xiubo Geng, Yining Chen, Fei Xu, Daxin Jiang. Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewriting. NAACL 2022.
• Yufei Wang, Can Xu, Qingfeng Sun, Huang Hu, Chongyang Tao, Xiubo Geng, Daxin Jiang. Prompt-based Data Augmentation for Low-Resource NLU Tasks. ACL 2022.
• Yucheng Zhou, Tao Shen, Xiubo Geng, Guodong Long, Daxin Jiang. ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification. ACL 2022.
• Jia-Chen Gu, Chao-Hong Tan, Chongyang Tao, Zhen-Hua Ling, Huang Hu, Xiubo Geng, Daxin Jiang. HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party Conversations. ACL 2022.
• Qingfeng Sun, Yujing Wang, Can Xu, Kai Zheng, Yaming Yang, Huang Hu, Fei Xu, Jessica Zhang, Xiubo Geng, Daxin Jiang. Multimodal Dialogue Response Generation. ACL 2022.
• Chao-Hong Tan, Jia-Chen Gu, Chongyang Tao, Zhen-Hua Ling, Can Xu, Huang Hu, Xiubo Geng, Daxin Jiang. TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge. ACL 2022 Findings.
• Yucheng Zhou, Xiubo Geng, Tao Shen, Guodong Long, Daxin Jiang. EventBERT: A Pre-Trained Model for Event Correlation Reasoning. WWW 2022.

2021

• Zujie Liang, Huang Hu, Can Xu, Jian Miao, Yingying He, yining Chen, Xiubo Geng, Fan Liang and Daxin Jiang. Learning Neural Templates for Recommender Dialogue System. EMNLP 2021.
• Qian Liu, Xiubo Geng, Heyan Huang; Tao Qin; Jie Lu; Daxin Jiang. MGRC: An End-to-End Multi-Granularity Reading Comprehension Model for Question Answering. The IEEE Transactions on Neural Networks and Learning System (TNNLS).
• Hao Huang, Xiubo Geng, Jian Pei, Guodong Long, Daxin Jiang. Reasoning over Entity-Action-Location Graph for Procedural Text Understanding. ACL-IJCNLP 2021 main conference.
• Jia-Chen Gu, Chongyang Tao, Zhenhua Ling, Can Xu, Xiubo Geng, Daxin Jiang. MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding. ACL-IJCNLP 2021 main conference.
• Zujie Liang, Huang Hu, Can Xu, Chongyang Tao, Xiubo Geng, yining Chen, Fan Liang, Daxin Jiang. Maria: A Visual Experience Powered Conversational Agent. ACL-IJCNLP 2021 main conference.
• Yucheng Zhou, Xiubo Geng, Tao Shen, Jian Pei, Wenqiang Zhang, Daxin Jiang. Modeling Event-Pair Relations in External Knowledge Graphs for Script Reasoning. ACL-IJCNLP 2021 Findings.
• Yucheng Zhou, Xiubo Geng, Tao Shen, Wenqiang Zhang, Daxin Jiang. Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph. NAACL-HLT 2021.
• Qian Liu, Xiubo Geng, Jie Lu, Daxin Jiang. Pivot-Based Candidate Retrieval for Cross-lingual Entity Linking. WWW 2021.
• Zhihan Zhang, Xiubo Geng, Tao Qin, Yunfang Wu, Daxin Jiang. Knowledge-Aware Procedual Text Understanding with Multi-Stage Training. WWW 2021.

2020

• Mucheng Ren, Xiubo Geng, Tao Qin, Heyan Huang, Daxin Jiang. Towards Interpretable Reasoning over Paragraph Effects in Situation. EMNLP 2020.
• Ping Nie, Yuyu Zhang, Xiubo Geng, Arun Ramamurthy, Le Song, Daxin Jiang. DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding. SIGIR 2020 short.
• Tao Shen, Xiubo Geng, Tao Qin, Guodong Long, Jing Jiang, Daxin Jiang. Effective Search of Logical Forms for Weakly Supervised Knowledge-Based Question Answering. IJCAI-PRICAI 2020.

2019 and Before

• Tao Shen, Xiubo Geng, Tao Qin, Daya Guo, Duyu Tang, Nan Duan, Guodong Long, Daxin Jiang. Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base. EMNLP-IJCNLP 2019.
• Shuzi Niu, Yanyan Lan, Jiafeng Guo, Xueqi Cheng, Xiubo Geng. What Makes Data Robust: A Data Analysis in Learning to Rank. SIGIR 2014 short.
• Xiubo Geng, Xin Fan, Jiang Bian, Xin Li, Zhaohui Zheng. Optimizing User Exploring Experience in Emerging E-Commerce Products. WWW 2012.
• Tao Qin, Xiubo Geng, Tie-Yan Liu. A New Probabilistic Model for Rank Aggregation. NIPS 2010.
• Xiubo Geng, Tie-Yan Liu, Tao Qin, Andrew Arnold, Hang Li, Heung-Yeung Shum. Query dependent ranking using k-nearest neighbor. SIGIR 2008.
• Xiubo Geng, Tie-Yan Liu, Tao Qin, Hang Li. Feature Selection for Ranking. SIGIR 2007.

Tutorials

• Tutorial on language scaling: Applications, Challenges and Approach at KDD 2021
• Tutorial on language scaling: Applications, Challenges and Approach at WWW 2021

Contact

Email: xigeng@microsoft.com

Address: 5 Danling Street, Haidian District Beijing, China, 100080