Happiness is when what you think, what you say, and what you do are in harmony.
-- Mahatma Gandhi

Jai Gupta Chair Associate Professor
Department of Computer Science and Engineering
Room 402, School of IT Building
Indian Institute of Technology Delhi
Hauz Khas, New Delhi, 110016, India

Affiliate Faculty
Department of Computer Science and Engineering
Paul Allen Center, Box 352350
University of Washington
Seattle, Washington, 98195, U.S.A.

Email : mausam AT cse DOT iitd DOT ac DOT in, mausam AT cs DOT washington DOT edu
Phone : +91-11-2659-6076 (O), +1-206-979-7038 (C)
Picture of Mausam

I am looking for technically strong and ambitious PhD students interested in applications of artificial intelligence (machine learning, natural language processing, crowdsourcing, automated planning). Please contact me if you are one of them. I am also interested in industry related problems that can be solved using AI techniques. Contact me if you think you have an interesting problem.

I am not looking for winter/summer interns or students for short-term (less than a year) projects. Please do not contact me with such requests. I am unable to respond to them personally.

ArnetMiner believes that I am the 25th most influential scholar in AI for 2019. Not sure I deserve to be in this list of AI greats, but happy to receive the honor, nonetheless!
In Jun'19 I gave bites to an Economics Times article on AI and India.
In Feb'19, I received the Jai Gupta Chair fellowship by IIT Delhi.
In Feb'19 I was interviewed by Factor Daily. The transcript of the interview.
In Oct'18 I was honored to participate in a Niti Aayog panel on AI in front of esteemed audience comprising the PM, council of ministers, heads of PSUs and senior bureaucrats in the Govt of India.
In Oct'18 I was interviewed as one of the experts for a Lok Sabha TV program on AI (in Hindi).
In Sep'18 my first NIPS NeurIPS paper got accepted!
In Sep'18 I was interviewed as one of the experts for Rajya Sabha TV features on AI: the video in English and the video in Hindi.
In Aug'18 I gave bites to an India Today article on the future of AI.
In Jan'18 I recorded a public talk on Artificial Intelligence: Past, Present and Future and a Student Q&A session for Living Science.
In Jun'17 I was a Program co-chair for the 27th International Conference on Automated Planning and Scheduling in Pittsburgh.
In Jul'16 I was invited to deliver a talk in the Early Career Spotlight Track at IJCAI'16 in New York.
In Jul'16 our STARAI'16 paper titled Contextual Symmetries in Probabilistic Graphical Models received the best paper award.
In Jun'16 I was elected as a councilor to AAAI Executive Council. Send me email if you have specific agenda items for AAAI Council meetings.
In Apr'16 I was awarded a Young Faculty Research Fellowship under the Visvesvaraya PhD scheme for Electronics & IT by Govt. of India.
In Apr'16 I was interviewed by ML India. The transcript of the interview.
In Aug'15 we released the first version of the Data Analytics & Intelligence Research (DAIR) group website.
In Jan'15 at AAAI'15, I was awarded the AAAI Senior status, a distinction in the field of artificial intelligence.
In Jan'15 I was awarded a Teaching Excellence Award for my Spring 2014's AI course.
In Sep'14 I appeared on NDTV Profit to defend Artificial Intelligence at a debate show titled, The Contrarian.
At HCOMP'13 our paper titled Crowdsourcing Multi-Label Classification for Taxonomy Creation received the best paper award.
In Oct'13 I joined as a faculty member at IIT Delhi after a six year research faculty stint at University of Washington, Seattle.
In July'12 Andrey Kolobov and I released a monograph titled Planning with Markov Decision Processes: An AI Perspective.

At present I am working on the following projects:
  • Open Information Extraction: We hope to overcome the "knowledge-acquisition bottleneck" by automatically extracting information from natural language text in a domain-independent manner. We work on improving the quality of Open IE extractors by pushing their precision and recall. Our recentmost Open IE extractor (Open IE 5) is publicly available. Recent progress on this work includes a better handling of compound noun expressions, numerical facts and lists of facts in a sentence. A short survey on the vast literature on Open IE.

  • Inference over Knowledge-Bases: Knowledge-bases are always incomplete! We develop novel inference algorithms for the task of knowledge-base completion. Our first model mitigates the issues with matrix factorization for this task. Our second model adds unsupervised typing to tensor factorization to obtain state of the art results on several datasets. We also release the code that implements these models. We also release a cleaned set of Open IE inference rules -- it uses linguistic rewrites for cleaning a statistically harvested set of inference rules.

  • Machine Learning over Crowdsourced Training Data: Does Machine Learning change when training data is generated over crowdsourcing? Yes. We first study the quality-size tradeoff in building training datasets. We extend active learning to "Re-Active Learning", which allows the same data point to be relabeled by a different worker over the crowdsourced platform. Finally, we devise novel algorithms in scenarios when data has severe class imbalance.

  • Abstractions in Machine Learning: We hope to exploit symmetries and other implicit domain abstractions to scale up a variety of machine learning and inference algorithms. We have developed symmetry-aware UCT algorithms in MDPs (Paper 1, Paper 2). We have also devised novel notions of symmetries such as contextual symmetries, variable-value symmetries, and block-value symmetries in probabilistic graphical models for downstream inference via Monte-Carlo sampling. We work on reducing computation in Markov Decision Process (MDP) algorithms such as UCT by aggregating symmetric states and state-action pairs. We also work on exploiting similar properties in the context of probabilistic inference. A recent paper on this work.

  • Neural Models for Probabilistic Planning: Neural models for reinforcement learning problems have achieve tremendous recent success. In this project, we study whether they can also be helpful for Markov Decision Processes (MDPs) that are expressed in a declarative logic-based representation such as RDDL. In our recent paper, we show that neural models trained on a few instances of a domain can be effectively transferred to a new instance of the same domain.

  • Applications of Open IE: Open Information Extraction is a domain-independent knowledge representation language that is different from linguistic suggestions such as semantic role labeling or domain-specific ontologies. We work on exploring the various applications that Open IE enables. We recently released OREO, a rapidly retargetable software to map open extractions to a domain ontology. In this recent paper we show that Open IE representation beats dependency parsing, and semantic role labelers in learning useful word vector representations via deep learning. Earlier, in this paper we used Open IE to automatically induce domain-independent event schemas.

In my personal time, I can be found listening to, playing, or singing hindustani classical music. I performed with a Seattle light Indian music band called Pratidhwani (our last show was Kashish in December 2012). I was also involved with Seattle's local cricket tournament where I tried my fingers at off-spinning. Movies and cooking take up whatever remaining free time I have.

Here is a website I host that contains interesting links about hindustani classical music.