We aim to use psychological theories about interestingness, curiosity, and empathy as a basis to design a general model-based conversation framework and use the framework to build a social bot that can hold informative, coherent, engaging conversations adapted to each user dynamically using real-time information from the web.
Revanth Gangi Reddy - Team leader
Reddy is a first year PhD student at UIUC whose research interests are in natural language understanding, more specifically in question answering and information retrieval. He has published more than 10 research papers in these areas at multiple top-tier conferences, such as AAAI, EMNLP, ACL, SIGIR and COLING. More recently, his research is aimed at addressing the information need in news, with a goal of improving comprehension for news readers, that include public health analysts, defense experts and journalists.
Karan Aggarwal
Aggarwal is a first-year master's student, studying computer science at University of Illinois, Urbana- Champaign. His research interests lie in the area of natural language processing, parallel systems and networking. In the past he has worked on high compute cloud-based applications as well as recommender systems in the e-commerce space. More recently his research has been focused on application development catered towards effective use of cloud resources and recommendation algorithms popular in the advertising space.
Stuti Agrawal
Stuti Agrawal is a second-year undergraduate student studying computer science at the University of Illinois Urbana-Champaign. Her research interests lie in the field of natural language processing and machine learning. In the past, she has worked on research in natural language processing specifically, information retrieval.
Hao (Jack) Bai
Bai is a senior computer engineering student at Zhejiang University and University of Illinois Urbana-Champaign. He has researched topics in gradient-based methods, including NLP, CV, frameworks, and quantitative finance. He studied (NLP) task-oriented dialog systems, code generation models, (CV) multi-object tracking, surface registration, fine-grained instance segmentation and (Framework) distributed deep learning frameworks. He is currently (NLP) researching on open domain question answering and (Quants) earning Certificate in Quantitative Finance (CQF).
Sharath Chandra
Chandra is a first-year master’s student studying Computer Science at the University of Illinois Urbana-Champaign. His research interests lie in the field of Natural Language Processing and Human Computer Interaction. In the past, he has tech lead experience working in a SaaS and B2B based company exploring the field of NLP and also text/chat automation. Motivated by his experience, he plans to find ways of offering NLP as a more accessible tool to the people for everyday use.
Varun Goyal
Goyal is a first year master's student pursuing computer science at the University of Illinois Urbana-Champaign. His research interests are in Natural Language Processing, more specifically in Information Extraction and Text Summarization. He has previously also worked on Data Mining and Computer Vision techniques. He has researched on and experimented with convolutional time series modelling, image segmentation, object detection, and image captioning. Motivated by his experience, he wants to research multimodal information extraction for the better comprehension of the diverse and gigantic amounts of text and visual data available.
Keyu Han
Han is a second year master's student majoring in information management in the School of Information Sciences at University of Illinois at Urbana-Champaign in Champaign, Illinois, United States. She has experience in e-commerce projects.
Liliang Ren
Ren is a third-year PhD candidate in the Text Information Management and Analysis Group, affiliated with the Data and Information Systems Laboratory at University of Illinois Urbana-Champaign. Ren earned her master's degree at University of California San Diego in 2020, and her undergraduate degree at Shanghai Jiao Tong University in 2018.
Prathamesh Sonawane
Sonawane is a first year master's student, studying computer science at University of Illinois, Urbana- Champaign. His research interests lie in the area of natural language processing and computer vision, particularly information retrieval and understanding. In the past he has worked on named-entity recognition, sentiment analysis, entity resolution, object tracking, and generative models, among other topics in the field of artificial intelligence. More recently his research has been focused on model architectures for efficient information retrieval and applications of Computer vision in autonomous systems.
Mankeerat Sidhu
Sidhu is currently studying computer engineering as a second year undergraduate student at UIUC. His research interests are in natural language processing and audio digital signal processing, more specifically in long document summarization. In the future, he wishes to do a PhD and work on a long term goal of a better access to information, providing a structured knowledge sense that is easily adaptable, explainable and capable of reasoning. In his previous works, he has dealt with deploying the machine learning models onto various platforms and and providing a smooth user interface along a vast domain of applications.
Wentao Yao
Yao is a senior student majoring in computer engineering at Zhejiang University and University of Illinois Urbana- Champaign. His research interests include QA system design, Chatbot, big model deployment and optimization. He has done multiple projects in AI Teaching Chatbot design and AI model systems based on open-domain question answering. He has also participated in NVIDIA TensorRT Hackathon 2022 Transformer Model Optimization Contest, working on Transformer- based model optimization for AI inference.
ChengXiang Zhai - Faculty advisor
Zhai is a Donald Biggar Willett Professor in Engineering in the Department of Computer Science. His general interests are in developing all kinds of novel intelligent information systems to help people manage and exploit large amounts of data and augment human intelligence, especially text data.