Publications (AI)

  1. Hangfeng He, Mingyuan Zhang, Qiang Ning, and Dan Roth. “Foreshadowing the Benefits of Incidental Supervision.” arxiv
  2. Roshanak Mirzaee, Hossein Rajaby Faghihi, Qiang Ning, and Parisa Kordjamshidi. “SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning.” NAACL, 2021.
  3. Ben Zhou, Kyle Richardson, Qiang Ning, Tushar Khot, Ashish Sabharwal, and Dan Roth. “Temporal Reasoning on Implicit Events from Distant Supervision.” NAACL, 2021. arxiv
  4. Haoyang Wen, Yanru Qu, Heng Ji, Qiang Ning, Jiawei Han, Avi Sil, Hanghang Tong, and Dan Roth. “Event Time Extraction and Propagation via Graph Attention Networks.” NAACL, 2021.
  5. Kaifu Wang, Qiang Ning, and Dan Roth. “Learnability with Indirect Supervision Signals.” NeurIPS, 2020. arxiv
  6. Matt Gardner et al. “Evaluating Models’ Local Decision Boundaries via Contrast Sets.” Findings of EMNLP, 2020. arxiv
  7. Qiang Ning, Hao Wu, Rujun Han, Nanyun Peng, Matt Gardner, and Dan Roth. “TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions.” EMNLP, 2020. website dataset talk arxiv
  8. Qiang Ning, Hao Wu, Pradeep Dasigi, Dheeru Dua, Matt Gardner, Robert L. Logan IV, Ana Marasovic, and Zhen Nie. “Easy, Reproducible and Quality-Controlled Data Collection with CROWDAQ.” EMNLP, 2020 (demo paper). website arxiv
  9. Hangfeng He, Qiang Ning, and Dan Roth. “QuASE: Question-Answer Driven Sentence Encoding.” ACL, 2020. arxiv
  10. Ben Zhou, Qiang Ning, Daniel Khashabi, and Dan Roth. “Temporal Common Sense Acquisition with Minimal Supervision.” ACL, 2020. arxiv
  11. Haoruo Peng, Qiang Ning, and Dan Roth. “KnowSemLM: A Knowledge Infused Semantic Language Model.” CoNLL, 2019. [website] [talk] [github]
  12. Rujun Han, Qiang Ning, and Nanyun Peng. “Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction.” EMNLP, 2019. [pdf] [poster] [github]
  13. Ben Zhou, Daniel Khashabi, Qiang Ning, and Dan Roth. “‘Going on a vacation’ takes longer than ‘Going for a walk’: A Study of Temporal Commonsense Understanding.” EMNLP, 2019 (short paper). [website] [talk slides] [talk pdf] [github]
  14. Qiang Ning, Sanjay Subramanian, and Dan Roth. “An Improved Neural Baseline for Temporal Relation Extraction.” EMNLP, 2019 (short paper). [website] [poster] [github]
  15. Eric Graves, Qiang Ning, and Prithwish Basu. “An information theoretic model for summarization, and some basic results.” IEEE International Symposium on Information Theory (ISIT), 2019. [pdf] [slides]
    • Understanding text summarization from a perspective of information theory.
  16. Qiang Ning, Hangfeng He, Chuchu Fan, and Dan Roth. “Partial or Complete, That’s The Question.” NAACL, 2019. [website] [pdf] [poster]
  17. Qiang Ning, Ben Zhou, Zhili Feng, Haoruo Peng, and Dan Roth. “CogCompTime: A Tool for Understanding Time in Natural Language Text.” EMNLP, 2018 (demo paper). [website] [pdf] [poster] [online demo][github].
    • A state-of-the-art automatic tool for:
    • Time expression extraction and normalization
    • Temporal relation extraction
  18. Qiang Ning, Hao Wu, and Dan Roth. “A Multi-Axis Annotation Scheme for Event Temporal Relations.” ACL, 2018. [website] [pdf] [Annotation Guidelines] [talk] [github:MATRES]
    • A new crowdsourcing annotation scheme for collecting temporal relation data more reliably and more efficiently
    • Achieved approx. 20% improvement in performance
  19. Qiang Ning, Zhili Feng, Hao Wu, and Dan Roth. “Joint Reasoning for Temporal and Causal Relations.” ACL, 2018. [website] [pdf] [talk] [github:TCR]
  20. Qiang Ning, Zhongzhi Yu, Chuchu Fan, and Dan Roth. “Exploiting Partially Annotated Data in Temporal Relation Extraction.” *SEM, 2018 (short paper). [website] [pdf] [poster] [github]
    • Incidental supervision for temporal relation extraction
  21. Qiang Ning, Hao Wu, Haoruo Peng, and Dan Roth. “Improving Temporal Relation Extraction with a Globally Acquired Statistical Resource.” NAACL, 2018. [website] [pdf] [poster] [github:TemProb] [Download TemProb]
    • Knowledge-base encoding prior statistics
    • For example, “die” should be after “explode”, instead of before; “ask” should be before “help” instead of after
    • Mined from a million NYT news articles using Amazon Web Services (AWS)
  22. Qiang Ning, Zhili Feng, and Dan Roth. “A Structured Learning Approach to Temporal Relation Extraction.” EMNLP, 2017. [website] [pdf] [talk] [github]
    • Structured Learning
    • Constraint-Driven Learning (CoDL)
  23. Qiang Ning, Kan Chen, Li Yi, Chuchu Fan, Yao Lu, and Jiangtao Wen. “Image Super-Resolution via Analysis Sparse Prior.” IEEE Signal Processing Letters, vol. 20, no. 4, p399-402, April 2013. [pdf] [code]
    • Image reconstruction/super-resolution
    • Compressed sensing


  1. Roadmap of word embedding techniques and how that leads to BERT [pdf] [pptx]
  2. A brief review of tensor decomposition [pdf]
  3. A brief review of graph2vec [pdf]
  4. A brief review of some bounds [pdf]
  5. Cramer-Rao bounds and its application to spectral quantification in MRS [pdf]
  6. A brief review of matrix derivatives and descend optimization methods [pdf]
  7. Gradient calculation for nonlinear least squares problems with complex numbers [pdf]
  8. A proof of the VARiable PROjection (VARPRO) method in Hilbert space [pdf]
  9. An introduction to one-class classification. [pdf]
  10. Qualifying Exam [pdf]


  1. CN2012105247162, granted April 17, 2013.