CONTACT
Language TechnologiesResearch Centre (LTRC)

IREL

Information Retrieval and Extraction Lab

Solving research problems in Information Retrieval, Extraction and Access.

About the Lab

The Information Retrieval and Extraction Lab (iREL) focuses on solving research problems in the areas of Information Retrieval (IR), Extraction (IE) and Access (IA).

The lab's research spans social media analysis, summarization, semantic search, text generation, and cloud computing. Our research papers have been published at top conferences worldwide including AAAI, ACL, EMNLP, CIKM and more.

Our Research

Recent Publications

View all publications
XWikiGen: Cross-lingual Summarization for Encyclopedic Text Generation in Low Resource Languages
Dhaval Taunk, Shivprasad Sagare, Anupam Patil, Shivansh Subramanian, Manish Gupta, Vasudeva Varma
WWW 2023
XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages
Tushar Abhishek, Shivprasad Sagare, Bhavyajeet Singh, Anubhav Sharma, Manish Gupta, Vasudeva Varma
WWW 2022
Categorizing Sexism and Misogyny through Neural Approaches
Pulkit Parikh, Harika Abburi, Niyati Chhaya, Manish Gupta, Vasudeva Varma
ACM TWEB 2021

Research Areas

Information Retrieval

Research on semantic search, cross-language information retrieval, and personalized information access systems.

Social Media Analysis

Mining and analyzing social media content for insights, trend detection, and sentiment analysis.

Text Summarization

Automatic summarization techniques for generating concise representations of large text documents.

Text Generation

Natural language generation systems for producing coherent and contextually appropriate text.

Projects

Project Angel

Active

An automated system that monitors activity on online social media platforms to identify and categorize adverse content, including hate speech and offensive language, followed by appropriate intervention strategies.

Text Style Transfer

Active

A pipeline that identifies the style of input text and translates it into a different style while preserving its core semantics. Partially funded by Adobe.

Indic Wikipedia

Active

Various avenues of work aimed at enhancing the Indian language content present on Wikipedia. Partially funded by PRIF (Govt. of Telangana) and MeitY.

Fake News Detection

Active

Design of algorithms to automatically detect news that is fake or can be attributed as propaganda, clickbait, or misrepresentation. Partially funded by Bharat Electronics.

Publications

XWikiGen: Cross-lingual Summarization for Encyclopedic Text Generation in Low Resource Languages
Dhaval Taunk, Shivprasad Sagare, Anupam Patil, Shivansh Subramanian, Manish Gupta, Vasudeva Varma
WWW 2023
XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages
Tushar Abhishek, Shivprasad Sagare, Bhavyajeet Singh, Anubhav Sharma, Manish Gupta, Vasudeva Varma
WWW 2022
Categorizing Sexism and Misogyny through Neural Approaches
Pulkit Parikh, Harika Abburi, Niyati Chhaya, Manish Gupta, Vasudeva Varma
ACM TWEB 2021
Adapting Language Models for Non-Parallel Author-Stylized Rewriting
Bakhtiyar Syed, Gaurav Verma, Balaji Vasan Srinivasan, Anandhavelu N, Vasudeva Varma
AAAI 2020
MVAE: Multimodal Variational Autoencoder for Fake News Detection
Dhruv Khattar, Jaipal Singh Goud, Manish Gupta, Vasudeva Varma
WWW 2019

Faculty

Vasudeva Varma
Professor & Centre Head
Ph.D (University of Hyderabad)
Information Retrieval, Social Media Analysis, Semantic Search, Cloud Computing
IREL
Manish Gupta
Adjunct Faculty
Ph.D (University of Illinois)
Web Mining, Data Mining, Databases, Algorithms
IREL
Niyati Chhaya
Adjunct Faculty
Ph.D (University of Maryland Baltimore County)
Effective Computing, Computational Linguistics, NLP, Machine Learning
IREL