Publications

2024

• Zhao Yang, Yuanzhe Zhang, Pengfei Cao, Cao Liu, Jiansong Chen, Jun Zhao, and Kang Liu. 2024. Information bottleneck based knowledge selection for commonsense reasoning. Information Sciences, 660:120134.

2023

• Zhao Yang, Yuanzhe Zhang, Dianbo Sui, Yiming Ju, Jun Zhao, and Kang Liu. 2023. Explanation Guided Knowledge Distillation for Pre-trained Language Model Compression. ACM Transactions on Asian and Low-Resource Language Information Processing:3639364.
• Zhao Yang, Yuanzhe Zhang, Dianbo Sui, Cao Liu, Jun Zhao, and Kang Liu. Representative Demonstration Selection for In-Context Learning with Two-Stage Determinantal Point Process. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5443–5456, Singapore. Association for Computational Linguistics.
• Zhongtao Jiang, Yuanzhe Zhang, Cao Liu, Jun Zhao, and Kang Liu. Generative Calibration for In-context Learning. Findings of the Association for Computational Linguistics: EMNLP 2023, pages 2312–2333, Singapore. Association for Computational Linguistics.
• Yifan Wei, Yisong Su, Huanhuan Ma, Xiaoyan Yu, Fangyu Lei, Yuanzhe Zhang, Jun Zhao, and Kang Liu. MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language Models. Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1434–1447, Singapore. Association for Computational Linguistics.
• Yiming Ju, Yuanzhe Zhang, Kang Liu, and Jun Zhao. A hierarchical explanation generation method based on feature interaction detection. In Findings of the Association for Computational Linguistics: ACL 2023, pages 12600–12611, Toronto, Canada, July 2023. Association for Computational Linguistics.
• Zhongtao Jiang, Yuanzhe Zhang, Cao Liu, Jiansong Chen, Jun Zhao, and Kang Liu. Interpreting sentiment composition with latent semantic tree. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7464–7478, Toronto, Canada, July 2023. Association for Computational Linguistics.

2022

• Yiming Ju, Yuanzhe Zhang, Zhao Yang, Zhongtao Jiang, Kang Liu and Jun Zhao. Logic Traps in Evaluating Attribution Scores. In Proceedings of ACL 2022, Dublin, Ireland, May 22-27.
• Yiming Ju, Weikang Wang, Yuanzhe Zhang, Suncong Zheng, Kang Liu and Jun Zhao. CMQA: A dataset of conditional question answering with multiple-span answers. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1697–1707, Gyeongju, Republic of Korea, October 2022. International Committee on Computational Linguistics.
• Zhao Yang, Yuanzhe Zhang, Zhongtao Jiang, Yiming Ju, Jun Zhao, and Kang Liu. 2022. Can We Really Trust Explanations? Evaluating the Stability of Feature Attribution Explanation Methods via Adversarial Attack. In Chinese Computational Linguistics, pages 281–297, Cham. Springer International Publishing.

2021

• Yiming Ju, Yuanzhe Zhang, Zhixing Tian, Kang Liu, Xiaohuan Cao, Went-ing Zhao, Jinlong Li, and Jun Zhao. Enhancing multiple-choice machinereading comprehension by punishing illogical interpretations. In Proceed-ings of the 2021 Conference on Empirical Methods in Natural LanguageProcessing, pages 3641–3652, Online and Punta Cana, Dominican Repub-lic, November 2021.
• Cheng Yan, Yuanzhe Zhang, Kang Liu, Jun Zhao, Yafei Shi, and Sheng-ping Liu. Biomedical concept normalization by leveraging hypernyms. InProceedings of the 2021 Conference on Empirical Methods in Natural Lan-guage Processing, pages 3512–3517, Online and Punta Cana, DominicanRepublic, November 2021.
• Zhongtao Jiang, Yuanzhe Zhang, Zhao Yang, Jun Zhao, and Kang Liu. Alignment rationale for natural language inference. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 5372–5387, Online, August 2021.
• Tian Zhixing, Zhang Yuanzhe, Liu Kang, and Zhao Jun. 2021. Topic Knowledge Acquisition and Utilization for Machine Reading Comprehension in Social Media Domain. In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 988–999, Huhhot, China. Chinese Information Processing Society of China.

2020 and Before

• Yuanzhe Zhang, Zhongtao Jiang, Tao Zhang, Shiwan Liu, Jiarun Cao, Kang Liu, Shengping Liu, and Jun Zhao. MIE: A medical information extractor towards medical dialogues. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), pages 6460–6469, Online, July 2020. Association for Computational Linguistics.
• Zhixing Tian, Yuanzhe Zhang, Xinwei Feng, Wenbin Jiang, Yajuan Lyu, Kang Liu, and Jun Zhao. Capturing sentence relations for answer sentenceselection with multi-perspective graph encoding. InProceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 9032–9039, 2020.
• Zhixing Tian, Yuanzhe Zhang, Kang Liu, Jun Zhao, Yantao Jia, and Zhicheng Sheng. Scene restoring for narrative machine reading comprehen-sion. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3063–3073, Online, November 2020.Association for Computational Linguistics.
• Delai Qiu, Yuanzhe Zhang, Xinwei Feng, Xiangwen Liao, Wenbin Jiang, Yajuan Lyu, Kang Liu, and Jun Zhao. Machine reading comprehensionusing structural knowledge graph-aware network. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP), pages 5896–5901, Hong Kong, China, November 2019.Association for Computational Linguistics.
• Delai Qiu, Liang Bao, Zhixing Tian, Yuanzhe Zhang, Kang Liu, Jun Zhao, and Xiangwen Liao. Reconstructed option rereading network for opinionquestions reading comprehension. In China National Conference on Chinese Computational Linguistics, pages 93–104. Springer, 2019. (Best Paper Award)
• Yanchao Hao, Yuanzhe Zhang, Kang Liu, Shizhu He, Zhanyi Liu, Hua Wu,and Jun Zhao. An end-to-end model for question answering over knowledgebase with cross-attention combining global knowledge. InProceedings ofthe 55th Annual Meeting of the Association for Computational Linguistics (ACL), pages 221–231, Vancouver, Canada, July 2017.Association for Computational Linguistics.
• Yuanzhe Zhang, Shizhu He, Kang Liu, and Jun Zhao. A joint model forquestion answering over multiple knowledge bases. In Proceedings of theAAAI Conference on Artificial Intelligence, volume 30, 2016.
• Kang Liu, Jun Zhao, Shizhu He, and Yuanzhe Zhang. Question answeringover knowledge bases. IEEE Intelligent Systems, 30(5):26–35, 2015.