Liyan Xu

About Me

I am currently a Research Scientist at WeChat AI, Tencent, focusing on Natural Language Processing (NLP). I graduated with PhD of Computer Science from Emory, advised by Dr. Jinho Choi. I was also co-advised by Dr. Fei Liu in 2023.

Before Emory, I completed my bachelor’s degrees at ECNU and CSU. Following this, I worked as a Software Engineer in US for two years before returning to graduate school.

Research Interests

My current research interests focus around RAG / Discourse Understanding / Memory with LLMs.

Actively looking for motivated students to collaborate on NLP research.

News

• [09/2024]: one paper got accepted by: EMNLP 2024 Findings.
• [05/2024]: three papers got accepted by: ACL / ICML / AAAI 2024.
• [06/2023]: started Research Scientist @ WeChat AI.
• [05/2023]: completed my PhD journey @ Emory!
• [05/2023]: one paper got accepted by: ACL 2023.
• [05/2022]: started Applied Scientist Intern @ Amazon Product Graph.
• [04/2022]: three papers got accepted by: NAACL / ICASSP / AAAI 2022.
• [08/2021]: one paper got accepted by: EMNLP 2021.
• [08/2021]: 1st place of CODI-CRAC 2021 shared task on anaphora resolution.
• [05/2021]: started Applied Scientist Intern @ Amazon Alexa ASR.
• [10/2020]: started research collaboration @ NEC Labs America.
• [09/2020]: one paper got accepted by: EMNLP 2020.
• [08/2020]: winning team of the 2020 Amazon Alexa Prize Chatbot Competition.

Selected Publications

• DBudgetKV: Dynamic Budget in KV Cache Compression for Ensuring Optimal Performance
  Xuanfan Ni^*, Liyan Xu^*, Chenyang Lyu, Longyue Wang, Mo Yu, Lemao Liu, Fandong Meng, Jie Zhou, Piji Li
  arXiv preprint 2502.16886

• Identifying Factual Inconsistencies in Summaries: Grounding Model Inference via Task Taxonomy
  Liyan Xu^*, Zhenlin Su^*, Mo Yu, Jin Xu, Jinho D. Choi, Jie Zhou, Fei Liu
  [EMNLP’24 Findings] The 2021 Conference on Empirical Methods in Natural Language Processing.

• Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questions
  Liyan Xu, Jiangnan Li, Mo Yu, Jie Zhou
  [ACL’24] The 62nd Annual Meeting of the Association for Computational Linguistics.

• SIG: Speaker Identification in Literature via Prompt-Based Generation
  Zhenlin Su, Liyan Xu^†, Jin Xu^†, Jiangnan Li, Mingdu Huangfu
  [AAAI’24] The 38th AAAI Conference on Artificial Intelligence.

• Towards Open-World Product Attribute Mining: A Lightly-Supervised Approach
  Liyan Xu, Chenwei Zhang, Xian Li, Jingbo Shang, Jinho D. Choi
  [ACL’23] The 61st Annual Meeting of the Association for Computational Linguistics.

• Modeling Task Interactions in Document-Level Joint Entity and Relation Extraction
  Liyan Xu, Jinho D. Choi
  [NAACL’22] The 2022 Conference of the North American Chapter of the Association for Computational Linguistics.

• Online Coreference Resolution for Dialogue Processing: Improving Mention-Linking on Real-Time Conversations
  Liyan Xu, Jinho D. Choi
  [*SEM’22] The 11th Joint Conference on Lexical and Computational Semantics.

• RescoreBERT: Discriminative Speech Recognition Rescoring with BERT
  Liyan Xu, Yile Gu, Jari Kolehmainen, Haidar Khan, Ankur Gandhe, Ariya Rastrow, Andreas Stolcke, Ivan Bulyko
  [ICASSP’22] 2022 IEEE International Conference on Acoustics, Speech and Signal Processing.

• Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-Sentence Dependency Graph
  Liyan Xu, Xuchao Zhang, Bo Zong, Yanchi Liu, Wei Cheng, Jingchao Ni, Haifeng Chen, Liang Zhao, Jinho D. Choi
  [AAAI’22] The 36th AAAI Conference on Artificial Intelligence.

• COVID-19 Pandemic-Associated Changes in the Acuity of Brain MRI Findings: A Secondary Analysis of Reports Using Natural Language Processing
  Taejin L. Min, Liyan Xu, Jinho D. Choi, Ranliang Hu, Jason W. Allen, Christopher W. Reeves, Derek Hsu, Richard Duszak, Jeffrey M. Switchenko, Gelareh Sadigh
  Current Problems in Diagnostic Radiology, July–August 2022.

• Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation
  Liyan Xu, Xuchao Zhang, Xujiang Zhao, Haifeng Chen, Feng Chen, Jinho D. Choi
  [EMNLP’21] The 2021 Conference on Empirical Methods in Natural Language Processing.

• Adapted End-to-End Coreference Resolution System for Anaphoric Identities in Dialogues
  Liyan Xu, Jinho D. Choi
  The CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue.

• ELIT: Emory Language and Information Toolkit
  Han He, Liyan Xu, Jinho D. Choi
  arXiv preprint 2109.03903

• Revealing the Myth of Higher-Order Inference in Coreference Resolution
  Liyan Xu, Jinho D. Choi
  [EMNLP’20] The 2020 Conference on Empirical Methods in Natural Language Processing.

• Noise Pollution in Hospital Readmission Prediction: Long Document Classification with Reinforcement Learning
  Liyan Xu, Julien Hogan, Rachel E. Patzer, Jinho D. Choi
  [BioNLP’20] The 19th SIGBioMed Workshop on Biomedical Language Processing.

Professional Services

• Program Committee Member: ARR Rolling (ACL, EMNLP, NAACL), AAAI, NeurIPS, ICML, ICLR

Other Activities

I enjoy exploring Mother Nature and playing with my camera (my gallery).