Seminars

View all Seminars  |  Download ICal for this event

Integrating Knowledge and Reasoning in Vision & NLP through Neurosymbolic Methods

Series: Department Seminar

Speaker: Dr. Somak Aditya, IIT Kharagpur

Date/Time: Feb 24 10:00:00

Location: CSD (Room No. 102, First Floor)

Abstract:
Abstract: In the 2010s, as Deep Learning models took over as the state-of-the-art AI systems, a large sub-community recognized the need for integrating domain knowledge, and human know-how in such data-driven systems. I will discuss how the initial neurosymbolc solutions were used to integrate commonsense knowledge in applications such as visual question answering, visual puzzle solving. The advent of massively pretrained (Large) Language Models (from BERT to ChatGPT) challenged the perception that DL systems do not have domain knowledge. Even more so, Transformers were shown to be able to deductively reason over natural language, generate Temporal Logic proofs -- showing some reasoning ability.


Therefore, we set out to understand the extent of knowledge and reasoning in Language Models. We saw that there are a specific set of skills that these models lack. This move from missing

Speaker Bio:
Dr. Somak Aditya is currently an Assistant Professor in CSE, IIT Kharagpur (joined 2021). He was a postdoctoral researcher at Microsoft Research India for nearly 2 years, and a full time researcher at Adobe Research for 1.5 years. He did his PhD thesis on “Knowledge and Reasoning for Image Understanding'' from Arizona State University in 2018. He has a background in Knowledge Representation and Reasoning, NLP, and Machine Learning; and is experienced in conducting interdisciplinary research in the field of AI. After demonstrating the need for knowledge integration in vision and language, he has explored the same in the Marketing domain and in Natural Language Inference during his postdoctoral stints. Through four workshops in top conferences such as KR, IJCAI, CIKM, and CVPR, Somak Aditya has actively promoted knowledge integration, the need for reasoning (and neuro-symbolic systems) in the community. He was also a part of the organizing committee of IndoML 2021 (and 2022), an annually hosted pan-Indian symposium for Machine Learning. He has filed 2 patents and written over 25 research articles in top AI/NLP/CV conferences. He has served as the Area Chair in COLM 2024, EMNLP 2023, NAACL 2024, COLING 2024; and SPC member in AAAI (2023, 2024, 2025) and ECAI 2024; and was a visiting faculty at UKP Lab, TU Darmstadt. His research is funded by SERB, AI4CPS Hub, Microsoft, Rakuten, Toloka.

Host Faculty: R Govindarajan