You can reach me via Email : parag.jain@ed.ac.uk
* indicate equal contribution
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.
Scalable
Micro-planned Generation of Discourse from Structured Data
Anirban Laha*, Parag Jain*, Abhijit Mishra, Karthik Sankaranarayanan
Computational Linguistics Journal, 2019 -- [Code]
TLDR A modular, pipeline-based approach, for structured data to text. Our framework does not require task-specific parallel data.
✨In news: Powering Match Insights for 🎾 US Open by interfacing with structured knowledge bases. TOI Gadgetsnow IBM Article
Unsupervised Controllable Text Formalization
Parag Jain, Abhijit Mishra, Amar Prakash Azad, Karthik Sankaranarayanan
AAAI 2019 [Video] -- [Code]
TLDR Wake-sleep style algorithm for learning a controllable style transfer model in an unsupervised manner.
Unsupervised Neural Text Simplification
Sai Surya, Abhijit Mishra, Anirban Laha, Parag Jain, Karthik Sankaranarayanan
ACL 2019 [Code]
TLDR Adversarial loss based method for lexical and syntactic simplification without using parallel data.
A Mixed Hierarchical Attention based Encoder-Decoder
Approach for Standard Table Summarization
Parag Jain, Anirban Laha, Karthik Sankaranarayanan, Preksha Nema, Mitesh M Khapra, Shreyas Shetty
NAACL-HLT 2018 [Code]
TLDR Efficient hierarchical attention model for table-to-text with known table schema.
Generating Descriptions from Structured Data Using a
Bifocal Attention Mechanism and Gated Orthogonalization
Preksha Nema*, Shreyas Shetty*, Parag Jain*, Anirban Laha, Karthik Sankaranarayanan, Mitesh M
Khapra
NAACL-HLT 2018 [Video] -- [Code]
TLDR Propose a method to induce stay-on and never-look-back behavior for structured data summarization.
Metric Learning for Clustering in Streaming Large-Scale Data
Parag Jain,
IIT Hyderabad, 2015 Thesis
TLDR Efficient methods for metric learning in streaming data scenarios. We extend diffusion maps for incremental data using incremental SVD. Additionally, we propose an unsupervised information-theoretic metric learning method based on laplacian eigenmaps.
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]
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