Publications

As a researcher, I have had the opportunity to work in a wide range of fields such as computer vision, natural language processing, fundamental machine learning, deep learning, reinforcement learning, and information theory. On this page, I categorize my publications according to different topics.

Natural Language Processing:

Shallow Semantic Parsing

• [EACL, Findings 2023] PriMeSRL-Eval: A Practical Quality Metric for Semantic Role Labeling Systems Evaluation. Ishan Jindal, Alexandre Rademaker, Khoi-Nguyen Tran, Huaiyu Zhu, Hiroshi Kanayama, Marina Danilevsky, Yunyao Li
  [Code]
• [NAACL 2022] Label Definitions Improve Semantic Role Labeling. Li Zhang, Ishan Jindal, Yunyao Li
  [Code]
• [LREC 2022] Universal Proposition Bank 2.0. Ishan Jindal, Alexandre Rademaker, Michał Ulewicz, Linh Ha, Huyen Nguyen, Khoi-Nguyen Tran, Huaiyu Zhu, Yunyao Li
  [Project Page]   [Data]
• [NAACL, SUKI 2022] Is Semantic-aware BERT more Linguistically Aware? A Case Study on Natural Language Inference. Ling Liu, Ishan Jindal, Yunyao Li
  [Code]
• [EMNLP, Findings 2020] CLAR: A Cross-Lingual Argument Regularizer for Semantic Role Labeling. Ishan Jindal, Yunyao Li, Siddhartha Brahma, Huaiyu Zhu
• [Preprint 2020] Improved Semantic Role Labeling using Parameterized Neighborhood Memory Adaptation. Ishan Jindal, Ranit Aharonov, Siddhartha Brahma, Huaiyu Zhu, Yunyao Li

Open Information Extraction

• [EMNLP 2023]Abstractive Open Information Extraction
  Kevin Pei, Ishan Jindal, Kevin Chang
• [ACL 2023] When to Use What: An In-Depth Comparative Empirical Analysis of OpenIE Systems for Downstream Applications
  Kevin Song Pei, Ishan Jindal, Kevin Chang, Yunyao Li, ChengXiang Zhai

Robustness to Label Noise

• [NAACL 2019] An Effective Label Noise Model for DNN Text Classification. Ishan Jindal, Daniel Pressel, Brian Lester, Matthew Nokleby
  [Code]

Data Augmentation

• [NEJLT: Northern European Journal of Language Technology 2023] NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation. A joint work with 100+ researchers
  [Code]

Human-in-the-Loop Systems

• [EMNLP 2023] Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture
  Bingsheng Yao, Ishan Jindal, Lucian Popa, Yannis Katsis, Sayan Ghosh, Lihong He, Yuxuan Lu, Shashank Srivastava, Yunyao Li, James Hendler, Dakuo Wang
• [EMNLP, DASH 2022] A Comparative Analysis between Human-in-the-loop Systems and Large Language Models for Pattern Extraction Tasks
  Maeda F. Hanafi, Yannis Katsis, Ishan Jindal, Lucian Popa

---

Information Theory:

• [ICASSP 2019] Tensor matched kronecker-structured subspace detection for missing information Ishan Jindal, Matthew Nokleby
  In IEEE International Conference on Acoustics, Speech and Signal Processing
• [Journal 2018] Classification and representation via separable subspaces: Performance limits and algorithms Ishan Jindal, Matthew Nokleby
  In IEEE Journal of Selected Topics in Signal Processing
• [ISIT 2017] Performance limits on the classification of Kronecker-structured models Ishan Jindal, Matthew Nokleby
  In IEEE International Symposium on Information Theory
• [Asilomar 2017] Fast and compact Kronecker-structured dictionary learning for classification and representation Ishan Jindal, Matthew Nokleby
  In IEEE 51st Asilomar Conference on Signals, Systems, and Computers

---

Reinforcement Learning:

• [Big Data 2018] Optimizing taxi carpool policies via reinforcement learning and spatio-temporal mining Ishan Jindal, Zhiwei Tony Qin, Xuewen Chen, Matthew Nokleby, Jieping Ye
  In IEEE International Conference on Big Data (Big Data)
• [Preprint 2017] A Unified Neural Network Approach for Estimating Travel Time and Distance for a Taxi Trip Ishan Jindal, Zhiwei Tony Qin, Xuewen Chen, Matthew Nokleby, Jieping Ye
  Accepted at MLDM 2017 conference

---

Computer Vision:

Robustness to Label Noise

• [Book Chapter 2020] Deep Neural Networks for Corrupted Labels Ishan Jindal, Matthew Nokleby, Daniel Pressel, Xuewen Chen, Harpreet Singh
  In Book Deep Learning: Concepts and Architectures by Springer
• [CVPRW 2019] A Nonlinear, Noise-aware, Quasi-clustering Approach to Learning Deep CNNs from Noisy Labels. Ishan Jindal, Matthew S Nokleby, Daniel Pressel, Xuewen Chen
  In IEEEE CVPR 2019 workshop
• [ICDM 2016] Learning deep networks from noisy labels with dropout regularization. Ishan Jindal, Matthew Nokleby, Xuewen Chen
  In IEEE 16th International Conference on Data Mining (ICDM), ICDM 2016

Classification

• [GlobalSIP 2016] Dynamic scene classification using convolutional neural networks. Aalok Gangopadhyay, Shivam Mani Tripathi, Ishan Jindal, Shanmuganathan Raman
  In IEEE 2016 IEEE Global Conference on Signal and Information Processing
• [IConSIP 2016] Effective object tracking in unstructured crowd scenes. Ishan Jindal, Shanmuganathan Raman
  In IEEE 2016 International Conference on Signal and Information Processing
• [NCVPRIPG 2015] Semantic description of a video using representative frames. Ishan Jindal, Shanmuganathan Raman
  In IEEE 2015 Fifth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics

---

   [Back to Top]