Publications


2021

  • Robustness Gym: Unifying the NLP Evaluation Landscape[website][code][paper]

    Karan Goel*, Nazneen Fatema Rajani*, Jesse Vig, Samson Tan, Jason Wu, Stephan Zheng, Caiming Xiong, Mohit Bansal, Christopher Ré. In arXiv. * indicates equal contribution.

  • FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging [paper]

    Han Guo, Nazneen Fatema Rajani, Peter Hase, Mohit Bansal, Caiming Xiong. In arXiv.

2020

  • CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers [paper]

    Shiyang Li, Semih Yavuz, Kazuma Hashimoto, Jia Li, Tong Niu, Nazneen Fatema Rajani, Xifeng Yan, Yingbo Zhou, Caiming Xiong. In Proceedings of ICLR 2021.

  • Explaining and Improving Model Behavior with k Nearest Neighbor Representations [paper]

    Nazneen Fatema Rajani, Ben Krause, Wengpeng Yin, Tong Niu, Richard Socher, Caiming Xiong. In arXiv.

  • Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models [paper]

    Pascal Sturmfels, Jesse Vig, Ali Madani, Nazneen Fatema Rajani. In NeurIPS workshop on Machine Learning for Structural Biology and Learning Meaningful Representations of Life

  • CTRLsum: Towards Generic Controllable Text Summarization [paper]

    Junxian He, Wojciech Kryściński, Bryan McCann, Nazneen Fatema Rajani, Caiming Xiong. In arXiv.

  • Explaining Creative Artifacts [paper]

    Lav R. Varshney, Nazneen Fatema Rajani, Richard Socher. In Workshop on Human Interpretability in Machine Learning (WHI), at ICML 2020. * indicates equal contribution.

  • GeDi: Generative Discriminator Guided Sequence Generation [paper] [code] [blog][Venture Beat]

    Ben Krause*, Akhilesh Gotmare*, Bryan McCann, Nitish Shirish Keskar, Shafiq Joty, Richard Socher, Nazneen Fatema Rajani. In arXiv.

  • BERTology Meets Biology: Interpreting Attention in Protein Language Models [paper] [code] [blog]

    Jesse Vig, Ali Madani, Lav R. Varshney, Caiming Xiong, Richard Socher, Nazneen Fatema Rajani. In Proceedings of ICLR 2021. Shorter version accepted at ICML workshop on ML4SD 2020.

  • Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation [paper] [code][blog]

    Tianlu Wang, Xi Victoria Lin, Nazneen Fatema Rajani, Bryan McCann, Vicente Ordonez, Caiming Xiong. In Proceedings of ACL 2020.

  • ESPRIT: Explaining Solutions to Physical Reasoning Tasks [paper] [code] [blog]

    Nazneen Fatema Rajani*, Rui Zhang*, Yi Chern Tan, Stephan Zheng, Jeremy Weiss, Aadit Vyas, Abhijit Gupta, Caiming Xiong, Richard Socher, Dragomir Radev. In Proceedings of ACL 2020. * indicates equal contribution.

2019

  • ERASER: A Benchmark to Evaluate Rationalized NLP Models [paper] [code] [website] [blog]

    Jay DeYoung*, Sarthak Jain*, Nazneen Fatema Rajani*, Eric Lehman, Caiming Xiong, Richard Socher, Byron Wallace. In Proceedings of ACL 2020. * indicates equal contribution.

  • Explain Yourself! Leveraging Language Models for Commonsense Reasoning [paper] [slides][video] [blog] [data] [venturebeat] [datanami ] [zdnet] [siliconangle]

    Nazneen Fatema Rajani, Bryan McCann, Caiming Xiong, Richard Socher. In Proceedings of ACL 2019.

2018 and older

  • Explainable Improved Ensembling for Natural Language and Vision (Ph.D. Thesis) [paper][slides]
  • Stacking With Auxiliary Features for Visual Question Answering [pdf][poster]

    Nazneen Fatema Rajani and Raymond J. Mooney. In Proceedings of NAACL 2018.

  • Ensembling Visual Explanations for VQA [pdf][poster]

    Nazneen Fatema Rajani and Raymond J. Mooney. In Proceedings of the NIPS 2017 workshop on Visually-Grounded Interaction and Language (ViGIL).

  • Using Explanations to Improve Ensembling of Visual Question Answering Systems [paper][poster]

    Nazneen Fatema Rajani and Raymond J. Mooney. In Proceedings of the IJCAI 2017 Workshop on Explainable Artificial Intelligence (XAI).

  • Stacking With Auxiliary Features [pdf][slides][poster]

    Nazneen Fatema Rajani and Raymond J. Mooney. In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI-17).

  • Stacking With Auxiliary Features for Entity Linking in the Medical Domain [paper]

    Nazneen Fatema Rajani, Mihaela Bornea and Ken Barker. In Proceedings of the ACL 2017 workshop on BioNLP.

  • Stacking With Auxiliary Features: Improved Ensembling for Natural Language and Vision (Ph.D. proposal) [pdf][slides]
  • Combining Supervised and Unsupervised Ensembles for Knowledge Base Population [paper][poster]

    Nazneen Fatema Rajani and Raymond J. Mooney. EMNLP 2016.

  • Stacked Ensemble of Information Extractors for Knowledge Base Population [paper][slides][video]
  • Nazneen Fatema Rajani, Vidhoon Vishwanathan, Yinon Bentor, Raymond J. Mooney. ACL 2015.

  • Parallel k Nearest Neighbor Graph Construction Using Tree-Based Data Structures [pdf]
  • Nazneen Fatema Rajani, Kate McArdle, Inderjit Dhillon. KDD 2015 workshop.

  • Identifying Interestingness in Fashion E-commerce using Pinterest Data [paper]
  • Nazneen Fatema Rajani, Khashayar Rohanimanesh, Eduardo Oliveira. KDD 2015 workshop.

  • New Topic Detection in Microblogs and Topic Model Evaluation using Topical Alignment (Master's Thesis) [pdf]
  • Extracting Topics based on Author, Recipient and Content in Microblogs [paper]
  • Nazneen Fatema Rajani, Kate McArdle, Jason Baldridge. SIGIR 2014.

  • Social Media Analytics (Bachelor's Thesis) [paper]
  • Solution to the Tic-Tac-Toe Problem using Hamming Distance Approach in a Neural Network [paper]
  • Nazneen Fatema Rajani, Gaurav Dar, Rajoshi Biswas, Ramesha C.K. ISMS 2011.