avatar

Saurabh Srivastava सौरभ श्रीवास्तव

Ph.D. Student
George Mason University
ssrivas6 (at) gmu.edu


About Me

Hi there! I am a third-year PhD candidate in the Natural Language Processing group at George Mason University; advised by Dr. Ziyu Yao.

My research revolves around the field of Information Extraction and Generative AI, where I delve into extracting event-specific information from a wide array of sources, including emails, sentences, and documents. My ultimate goal is to contribute to the development of a versatile machine learning system capable of retrieving event-specific details from unstructured text and presenting them in a structured format, facilitating seamless further processing.

Recently, I have also focused on Prompt Optimization for LLMs to elicit correct zero-shot responses from both Open-Source and API-based LLMs. Please check the list of publications for more details.

Prior to my journey at GMU, I earned a master’s degree in Computer Science and Engineering from the Indian Institute of Technology - Patna. Additionally, I obtained a bachelor’s degree in Computer Science and Engineering from Uttar Pradesh Technical University. I have also served as an NLP researcher at Tata Research from 2017-2021.

In my free time, I make music for violin and piano. I enjoy the outdoors, particularly cricket, badminton and mountains.

Research Interests

News

Publications

  1. ArXiv
    Instances Need More Care: Rewriting Prompts for Instances with LLMs in the Loop Yields Better Zero-Shot Performance
    Saurabh Srivastava, Chengyue Huang, Weiguo Fan, Ziyu Yao
    ArXiv preprint, 2023.
    PDF Code
  2. EMNLP
    MAILEX: Email Event and Argument Extraction
    Saurabh Srivastava, Gaurav Singh, Shou Matsumoto, Ali Raz, Paulo Costa, Joshua Poore, Ziyu Yao
    EMNLP, 2023.
    PDF Code
  3. ACL
    Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing
    Hao Yan, Saurabh Srivastava, Yintao Tai, Sida I Wang, Wen-tau Yih, Ziyu Yao
    ACL, 2023.
    PDF Code
  4. Event Extraction on Email Conversations
    Saurabh Srivastava, Ziyu Yao
    MASC-2023.
    PDF
  5. Complex Question Answering on knowledge graphs using machine translation and multi-task learning
    Saurabh Srivastava, Mayur Patidar, Sudip Chowdhury, Puneet Agarwal, Indrajit Bhattacharya, Gautam Shroff
    EACL, 2021.
    PDF
  6. Capsule based neural network architecture to perform completeness check for patent eligibility process
    Saurabh Srivastava, Puneet Agarwal, Gautam Shroff, Lovekesh Vig, Vidya Vikas
    IJCNN, 2020.
    PDF
  7. A novel hierarchical BERT architecture for sarcasm detection
    Himani Srivastava, Vaibhav Varshney, Surabhi Kumari, Saurabh Srivastava
    ACL FigLang workshop, 2020.
    PDF
  8. Improved Question Answering using Domain Prediction
    Himani Srivastava, Prerna Khurana, Saurabh Srivastava, Vaibhav Varshney, Lovekesh Vig, Puneet Agarwal, Gautam Shroff,
    KDD Converse, 2020.
    PDF
  9. Detecting aggression and toxicity using a multi dimension capsule network
    Saurabh Srivastava, Prerna Khurana
    ACL Workshop, 2019.
    PDF
  10. Exploring machine learning and deep learning frameworks for task-oriented dialogue act classification
    Tulika Saha, Saurabh Srivastava, Mauajama Firdaus, Sriparna Saha, Asif Ekbal, Pushpak Bhattacharyya
    IJCNN, 2019.
    PDF
  11. Hierarchical capsule based neural network architecture for sequence labeling
    Saurabh Srivastava, Puneet Agarwal, Gautam Shroff, Lovekesh Vig
    IJCNN, 2019.
    PDF
  12. Identifying aggression and toxicity in comments using capsule network
    Saurabh Srivastava,Prerna Khurana, Vartika Tewari
    ACL TRAC workshop, 2018.
    PDF
  13. Experiments with Domain Dependent Dialogue Act Classification using Open-Domain Dialogue Corpora
    Swapnil Hingmire, Apoorv Shrivastava, Girish Palshikar, Saurabh Srivastava
    ICON 2017.
    PDF

Experience

Services

Organizing Committee

Program Committee Member

Secondary Reviewer

  • NeurIPS 2023 - Thirty-seventh Conference on Neural Information Processing Systems

    • Honors and Awards


    Powered by Jekyll and Minimal Light theme.