Indian Symposium on Machine Learning (IndoML)
December 16 – 18, 2021 | Virtual
The Second Indian Symposium on Machine Learning (IndoML) will be hosted by the Indian Institute of Technology Gandhinagar (IITGN) between 16-18 December 2021. The symposium aims to be a forum to discuss state-of-the-art ML research through invited talks from leading experts within India and abroad. IndoML fosters mentoring of Indian Ph.D./Master students to network with their peers, seek expert guidance and develop early-stage collaborations.
IndoML aims to provide an opportunity for the faculty to engage with leading research groups in the country and conduct high-quality research leading to competitive publications. It will also provide a platform for industrial partners, including startups, working in ML-related areas to showcase their products and receive reviews/feedback as well as setup potential collaborations.
Theme
The theme of IndoML 2021 is “AI for Data and Data for AI“
Organizers
-
IIT Gandhinagar:
Anirban Dasgupta, Mayank Singh, Udit Bhatia
-
IIT Kharagpur:
Animesh Mukherjee, Niloy Ganguly
-
Datathon Team:
Bidisha Samanta (Google Research India),
Jayesh Choudhari (University of Warwick),
Somak Aditya (IITKGP, previously Microsoft Research India),
Sandipan Sikdar (RWTH Aachen University, Germany)
-
Publicity Chair:
Vivek Srivastava (TCS Research Pune),
Ameena Khaleel (Google Research India)
Volunteers
-
IIT Kharagpur:
Abhilash Nandy, Arijit Nag, Souvic Chakraborty, Gunjan Balde
-
Carnegie Mellon University:
Pratik Joshi
Speakers
Abhijnan Chakraborty
Indian Institute of Technology Delhi, India
Chris Potts
Stanford University, California
Dipanjan Das
Google AI, New York
Dragomir R. Radev
Yale University, US
Ido Dagan
Bar-Ilan University, Israel
Iryna Gurevych
Technische Universität Darmstadt,Germany
Marinka Zitnik
Harvard University, US
Michael Bronstein
Imperial College London, London
Mohit Bansal
UNC Chapel Hill, USA
Monojit Choudhury
Microsoft Research Lab, India
Raymond J. Mooney
University of Texas at Austin, US
Robert Hoehndorf
King Abdullah University of Science and Technology, Saudi Arabia
Ronita Bardhan
University of Cambridge, UK
Sameer Singh
University of California, Irvine
Sharad Goel
Harvard University, US
Subimal Ghosh
IITB, India
Tavpritesh Sethi
IIIT Delhi, India
Thomas Vandal
NASA Earth eXchange, USA
Tim Baldwin
University of Melbourne, Australia
Udit Bhatia
IIT Gandhinagar, India
Vivek Raghavan
Chief Product Manager and Biometric Architect at UIDAI, India
Schedule
Mentioned time is Indian Standard Time (GMT+5 hr 30 mins)
Time
|
Talk |
Speaker |
Day 1 Session I: Responsible AI – Fairness and Interpretability
|
||
Session Chair: Mayank Singh (IITGN) |
||
08:00 – 08:15 |
Animesh Mukherjee: Inaugural talk |
 |
08:15 – 09:00 |
Sharad Goel: Designing Equitable Algorithms for Criminal Justice and Beyond |
|
09:00 – 09:45 |
Sameer Singh: Evaluating and Testing Natural Language Processing Models |
|
09:45 – 10:30 |
Tim Baldwin: Fairness in Natural Language Processing |
|
10:30 – 11:15 |
Abhijnan Chakroborty: Fair Partitioning of Public Resources:Countering Inequality in Public School Funding |
|
Day 1 Session II: ML in NLP |
||
Session Chair: Bidisha Samanta (Google Research India) |
||
16:00 – 16:45 |
Ido Dagan: Novel data for modeling textual information: decomposition, multi-text, and interaction |
|
16:45 – 17:30 |
Monojit Choudhury: Applications and Techniques for Code-mixed Text Generation |
|
17:30 – 18:15 |
Dragomir R. Radev: Closing the loop in natural language interfaces to databases: Parsing, dialogue, and generation |
|
Time (IST: GMT+5:30) |
Talk |
Speaker |
Day 3 Session I: ML applications beyond CS |
||
Session Chair: Abir Das (IITKGP) |
||
08:00 – 08:45 |
Thomas Vandal: GeoNEX-ML: A Machine Learning System for Earth Observations |
|
08:45 – 09:30 |
Subimal Ghosh: Data-Driven Modeling of Monsoon and its Characteristics |
|
09:30 – 10:15 |
Tavpritesh Sethi: What would an artificial intelligence augmented pandemic response look like? |
|
10:15 – 11.00 |
Jayesh Choudhari: Felicitation
|
|
Day 3 Session II: Ethics and trust in NLP |
||
Session Chair: Sandipan Sikdar (RWTH Aachen University) |
||
15:15 – 16:00 |
Vivek Raghavan: Creating Datasets for Public Good |
|
16:00 – 16:45 |
Michael Bronstein: Neural diffusion PDEs, differential geometry, and graph neural networks |
|
16:45 – 17:30 |
Iryna Gurevych: Towards consent-driven, ethically sound NLP for peer reviews |
|
17:30 – 18:15 |
Dipanjan Das: Trustworthy Natural Language Generation with Communicative Goals |
|
18:15 – 18:30 |
Anirban Dasgupta: Conclusion and Vote Of Thanks |
|
Datathon
Datathon is a part of the workshop named IndoML organized by a team consisting of academics and researchers from IIT Gandhinagar, IIT Kharagpur, University of Warwick, Google, and Microsoft Research with a theme of “Data for AI and AI for Data”. The broad aim of this Datathon is to invite participants to gain experience in solving real world data science/ML problems posed by experts in industry and academia.
As a part of Datathon-2021 following are the set of competitions:
1. GLUECoS-NLI-Knowledge: This is a Conversational Code-switched Natural Language Inference dataset, in English and Hindi (written in Roman script). Here, the premise is a multi-turn dialog and hypothesis is a sentence. The traditional NLI task is to determine whether the hypothesis is entailed by or contradicts with the premise (there are only 2 labels: entailment or contradiction unlike the popular NLI task). For this competition, the task is: given a premise-hypothesis pair (and the entailment label), the goal is to determine whether inferring the entailment label would require some sort of external knowledge or not. This problem is posed by Microsoft.
2. IndoRE: IndoRE is a relation extraction task for three low resource Indian Languages (Bengali, Telugu and Hindi) and this task is posed by IIT Kharagpur.
3. E-Manual: This is a question-answering task. Here the dataset is a set of manuals of electronic instruments, and the goal here is to extract an answer and/or the section from the manual where an answer is present for a given question. This problem statement is posed by IIT Kharagpur.
4. Multilingual Abusive Comment Identification: Multilingual Abusive Comment Identification Challenge is a challenge towards combating abusive comments (in multiple Indian regional languages) on Moj, which is one of India’s largest short-video apps. This challenge is posed by Sharechat.
5. COVID-19 India Dataset: Flex your brains on one of the most comprehensive sources of COVID data from India, extracted automatically from daily health bulletins published by major Indian states. This challenge is posted by IBM Research.
Participants will have an opportunity to win prizes worth up to 4 Lacs generously sponsored by ACM India and other companies including Microsoft Research India, Google, IBM Research and ShareChat!!!
Competition |
Team Names |
GLUECoS-NLI-Knowledge |
|
IndoRE |
|
E-Manual |
|
Multilingual Abusive Comment Identification |
1. Hate – Alert
|
Sponsors
