I'm a final year PhD student at the University of Edinburgh supervised by Prof. Mirella Lapata.
Previous affiliations: Intern@DeepMind, IBMResearch, Amazon.

I'm on the job market!

You can reach me via Email  : parag.jain@ed.ac.uk


     



News

  • Talk at IIT Hyderabad on "Structsum Generation for Faster Text Comprehension."
  • Paper accepted at ACL 2024 main track.
  • Attending EMNLP 2023.
  • Joined Google deepmind as a student researcher.
  • Paper accepted at ACL 2023.
  • I will be attending EACL 2023.
  • Internship offer from Google Research (Mountain View).
  • Paper accepted at EACL'23.
  • (July 2022) Attended student networking and presentations event at The Alan Turing Institute London.
  • (June 2022) Talk at APMCS Conference (virtually).
  • (2022) Attending ACL virtually.
  • I'm now on Twitter :) @jparag123
  • (2021) Presented our TACL work at EMNLP 2021.
  • Paper accepted at IKDD CODS 2021.


Selected Publication

* indicate equal contribution

Check full list here.

  • Integrating Large Language Models with Graph-based Reasoning for Conversational Question Answering
    Parag Jain, Mirella Lapata
    Under Review 2024
    TLDR We present a method to aggregate evidence from multiple sources into a dynamic graph for conversational question answering, efficiently integrating it with LLMs for end-to-end training. Past evidence is tracked in a memory module, which updates as the conversation evolves to influence the graph structure and representation.

  • Structsum Generation for Faster Text Comprehension
    Parag Jain, Andreea Marzoca, Francesco Piccinno
    ACL 2024
    TLDR We explore generating structured representations (Mind Maps 🧠 🗺 and Tables 📝 ) of text using LLMs. Via a user study, we show that structured representations reduce comprehension time for users compared to just plain text.

  • Conversational Semantic Parsing using Dynamic Context Graphs
    Parag Jain, Mirella Lapata
    EMNLP 2023 [Code]
    TLDR We model knowledge graph (KG) context as a dynamic context graph and implement a scalable method for context-dependent type linking. Our approach demonstrates improved performance on the SPICE dataset, which requires understanding long-range context.

  • Semantic Parsing for Conversational Question Answering over Knowledge Graphs
    Laura Perez-Beltrachini, Parag Jain, Emilio Monti, Mirella Lapata
    EACL 2023 [Dataset and Code]
    TLDR We create SPICE, a semantic parsing dataset for conversational question answering over Wikidata.

  • Multi-Document Summarization with Centroid-Based Pretraining
    Ratish Puduppully, Parag Jain, Nancy F. Chen, Mark Steedman
    ACL 2023 [Code]
    TLDR We introduce a novel pretraining objective for multi-document summarization, which involves selecting the ROUGE-based centroid of each document cluster as a proxy for its summary.

  • Memory-Based Semantic Parsing
    Parag Jain, Mirella Lapata
    TACL 2021 -- [Video] [Code]
    TLDR We propose to represent discourse information using a bounded external memory. Bounded memory helps process long interactions irrespective of conversation-length. Our memory is interpretable and is managed by a learned controller.

  • Unified Semantic Parsing with Weak Supervision
    Priyanka Agrawal, Parag Jain, Ayushi Dalmia, Abhishek Bansal, Ashish Mittal, Karthik Sankaranarayanan
    ACL 2019 [Code]
    TLDR We propose a multi-policy distillation based method for learning a unified semantic parser (student) using independent weakly supervised experts (teacher) for each domain. Individual experts are trained using the REINFORCE to maximize the expected denotation accuracy.


Talks and Tutorial


  • Talk at IIT Hyderabad on Structsum Generation for Faster Text Comprehension.

  • Foster Talk at Jabalpur Engineering College, 2023

  • Conversational Semantic Parsing - Online International. Conference. On. Advances in Physical, Mathematical and Computational Sciences, India - 2022

  • Storytelling from Structured Data and Knowledge Graphs : An NLG Perspective, Tutorial ACL 2019[Website]

  • Introduction to Machine Learning - Christ University Bangalore, 2018

  • Talk on Online Metric learning (IBM Research Bangalore, 2016) [Slides]


Teaching


  • Tutor for Natural Language Understanding, Generation, and Machine Translation, University of Edinburgh (2020-2021)

  • TA for Numerical Linear Algebra for Data Analysis (CS5270, 2015), IIT Hyderabad

  • TA for Introduction to Database Management Systems (CS3010/CS3011, 2014), IIT Hyderabad

  • TA for Advanced Compiler Design (CS6240, 2014), IIT Hyderabad