no code implementations • 16 Mar 2024 • Prayushi Faldu, Indrajit Bhattacharya, Mausam
We propose a new model for KBQA named RetinaQA that is robust against unaswerability.
no code implementations • 4 Feb 2024 • Chinmay Mittal, Krishna Kartik, Mausam, Parag Singla
Recent works show that the largest of the large language models (LLMs) can solve many simple reasoning tasks expressed in natural language, without any/much supervision.
1 code implementation • 29 Nov 2023 • Aayush Kumar Tyagi, Vaibhav Mishra, Prathosh A. P., Mausam
In response, we investigate guiding the prompting procedure in SAM for weakly supervised cell segmentation when only bounding box supervision is available.
no code implementations • 15 Nov 2023 • Mayur Patidar, Riya Sawhney, Avinash Singh, Biswajit Chatterjee, Mausam, Indrajit Bhattacharya
Additional experiments in the in-domain setting show that FuSIC-KBQA also outperforms SoTA KBQA models when training data is limited.
no code implementations • 14 Nov 2023 • Harshvardhan Srivastava, Kanav Pruthi, Soumen Chakrabarti, Mausam
End-to-end conversational recommendation systems (CRS) generate responses by leveraging both dialog history and a knowledge base (KB).
no code implementations • 7 Nov 2023 • Ananjan Nandi, Navdeep Kaur, Parag Singla, Mausam
We consider two popular approaches to Knowledge Graph Completion (KGC): textual models that rely on textual entity descriptions, and structure-based models that exploit the connectivity structure of the Knowledge Graph (KG).
1 code implementation • 25 Oct 2023 • Vipul Rathore, Rajdeep Dhingra, Parag Singla, Mausam
We posit that for more effective cross-lingual transfer, instead of just one source LA, we need to leverage LAs of multiple (linguistically or geographically related) source languages, both at train and test-time - which we investigate via our novel neural architecture, ZGUL.
1 code implementation • 19 Oct 2023 • Aman Madaan, Pranjal Aggarwal, Ankit Anand, Srividya Pranavi Potharaju, Swaroop Mishra, Pei Zhou, Aditya Gupta, Dheeraj Rajagopal, Karthik Kappaganthu, Yiming Yang, Shyam Upadhyay, Mausam, Manaal Faruqui
Large language models (LLMs) are now available from cloud API providers in various sizes and configurations.
no code implementations • 16 Oct 2023 • Anand Brahmbhatt, Vipul Rathore, Mausam, Parag Singla
Further, we show that ensuring group-wise calibration with respect to the sensitive attributes automatically results in a fair model under our definition.
1 code implementation • 12 Oct 2023 • Kausik Hira, Mohd Zaki, Dhruvil Sheth, Mausam, N M Anoop Krishnan
The discovery of new materials has a documented history of propelling human progress for centuries and more.
no code implementations • 17 Aug 2023 • Mohd Zaki, Jayadeva, Mausam, N. M. Anoop Krishnan
Further, we evaluate the performance of GPT-3. 5 and GPT-4 models on solving these questions via zero-shot and chain of thought prompting.
1 code implementation • 26 May 2023 • Vishal Vivek Saley, Rocktim Jyoti Das, Dinesh Raghu, Mausam
In this work, we define the novel problem of learning a TOD agent with dialog-KB inconsistencies in the training data.
1 code implementation • 24 May 2023 • Daman Arora, Himanshu Gaurav Singh, Mausam
In response, we present JEEBench, a considerably more challenging benchmark dataset for evaluating the problem solving abilities of LLMs.
Ranked #1 on Overall - Test on JEEBench
1 code implementation • 19 May 2023 • Pranjal Aggarwal, Aman Madaan, Yiming Yang, Mausam
A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency - poll the LLM multiple times and output the most frequent solution.
no code implementations • 15 May 2023 • Ishaan Singh, Navdeep Kaur, Garima Gaur, Mausam
While Knowledge Graph Completion (KGC) on static facts is a matured field, Temporal Knowledge Graph Completion (TKGC), that incorporates validity time into static facts is still in its nascent stage.
1 code implementation • CVPR 2023 • Aayush Kumar Tyagi, Chirag Mohapatra, Prasenjit Das, Govind Makharia, Lalita Mehra, Prathosh AP, Mausam
While there exist multiple, general-purpose, deep learning-based object detection and counting methods, they may not readily transfer to detecting and counting cells in medical images, due to the limited data, presence of tiny overlapping objects, multiple cell types, severe class-imbalance, minute differences in size/shape of cells, etc.
no code implementations • 20 Dec 2022 • Mayur Patidar, Prayushi Faldu, Avinash Singh, Lovekesh Vig, Indrajit Bhattacharya, Mausam
When answering natural language questions over knowledge bases, missing facts, incomplete schema and limited scope naturally lead to many questions being unanswerable.
1 code implementation • 13 Nov 2022 • Shubham Mittal, Keshav Kolluru, Soumen Chakrabarti, Mausam
Automated completion of open knowledge bases (Open KBs), which are constructed from triples of the form (subject phrase, relation phrase, object phrase), obtained via open information extraction (Open IE) system, are useful for discovering novel facts that may not be directly present in the text.
1 code implementation • 24 Oct 2022 • Keshav Kolluru, Gabriel Stanovsky, Mausam
Proper noun compounds, e. g., "Covid vaccine", convey information in a succinct manner (a "Covid vaccine" is a "vaccine that immunizes against the Covid disease").
1 code implementation • 17 Oct 2022 • Yatin Nandwani, Rishabh Ranjan, Mausam, Parag Singla
Experiments on several problems, both perceptual as well as symbolic, which require learning the constraints of an ILP, show that our approach has superior performance and scales much better compared to purely neural baselines and other state-of-the-art models that require solver-based training.
1 code implementation • 3 Jul 2022 • Tanishq Gupta, Mohd Zaki, Devanshi Khatsuriya, Kausik Hira, N. M. Anoop Krishnan, Mausam
A crucial component in the curation of KB for a scientific domain (e. g., materials science, foods & nutrition, fuels) is information extraction from tables in the domain's published research articles.
1 code implementation • 14 May 2022 • Shreya Sharma, Jigyasa Gupta, Shreshth Tuli, Rohan Paul, Mausam
Our goal is to enable a robot to learn how to sequence its actions to perform tasks specified as natural language instructions, given successful demonstrations from a human partner.
1 code implementation • 24 Feb 2022 • Kevin Leyton-Brown, Mausam, Yatin Nandwani, Hedayat Zarkoob, Chris Cameron, Neil Newman, Dinesh Raghu
Peer-reviewed conferences, the main publication venues in CS, rely critically on matching highly qualified reviewers for each paper.
no code implementations • ICLR 2022 • Yatin Nandwani, Vidit Jain, Mausam, Parag Singla
One drawback of the proposed architectures, which are often based on Graph Neural Networks (GNN), is that they cannot generalize across the size of the output space from which variables are assigned a value, for example, set of colors in a GCP, or board-size in sudoku.
1 code implementation • ACL 2022 • Vipul Rathore, Kartikeya Badola, Mausam, Parag Singla
The contextual embeddings of tokens are aggregated using attention with the candidate relation as query -- this summary of whole passage predicts the candidate relation.
1 code implementation • 30 Sep 2021 • Tanishq Gupta, Mohd Zaki, N. M. Anoop Krishnan, Mausam
Here, we present a materials-aware language model, namely, MatSciBERT, which is trained on a large corpus of scientific literature published in the materials domain.
no code implementations • Findings (ACL) 2021 • Dinesh Raghu, Atishya Jain, Mausam, Sachindra Joshi
In this paper, we propose a novel filtering technique that consists of (1) a pairwise similarity based filter that identifies relevant information by respecting the n-ary structure in a KB record.
1 code implementation • EMNLP 2021 • Dinesh Raghu, Shantanu Agarwal, Sachindra Joshi, Mausam
We propose a novel problem within end-to-end learning of task-oriented dialogs (TOD), in which the dialog system mimics a troubleshooting agent who helps a user by diagnosing their problem (e. g., car not starting).
no code implementations • 12 Jun 2021 • Prashant Pandey, Ajey Pai, Nisarg Bhatt, Prasenjit Das, Govind Makharia, Prathosh AP, Mausam
We evaluate our method on four public medical segmentation datasets and a novel histopathology dataset that we introduce.
no code implementations • 6 Jun 2021 • Ananye Agarwal, Pradeep Shenoy, Mausam
A key limitation is that such neural-to-symbolic models can only be trained end-to-end for tasks where the output space is symbolic.
1 code implementation • 5 May 2021 • Shreshth Tuli, Rajas Bansal, Rohan Paul, Mausam
We introduce a novel neural model, termed TANGO, for predicting task-specific tool interactions, trained using demonstrations from human teachers instructing a virtual robot.
no code implementations • 18 Apr 2021 • Keshav Kolluru, Mayank Singh Chauhan, Yatin Nandwani, Parag Singla, Mausam
Pre-trained language models (LMs) like BERT have shown to store factual knowledge about the world.
no code implementations • AKBC 2021 • Harkanwar Singh, Prachi Jain, Mausam, Soumen Chakrabarti
Almost all of existing KGC research is applicable to only one KG at a time, and in one language only.
Ranked #2 on Knowledge Graph Completion on DBP-5L (Greek)
1 code implementation • ACL 2022 • Abhyuday Bhartiya, Kartikeya Badola, Mausam
We show that these characteristics lead to a gross overestimation of the model performance.
1 code implementation • EMNLP 2020 • Keshav Kolluru, Vaibhav Adlakha, Samarth Aggarwal, Mausam, Soumen Chakrabarti
This IGL based coordination analyzer helps our OpenIE system handle complicated coordination structures, while also establishing a new state of the art on the task of coordination analysis, with a 12. 3 pts improvement in F1 over previous analyzers.
Ranked #1 on Open Information Extraction on WiRe57
1 code implementation • 28 Sep 2020 • Danish Contractor, Shashank Goel, Mausam, Parag Singla
In response, we develop the first joint spatio-textual reasoning model, which combines geo-spatial knowledge with information in textual corpora to answer questions.
no code implementations • ICLR 2021 • Yatin Nandwani, Deepanshu Jindal, Mausam, Parag Singla
Our framework uses a selection module, whose goal is to dynamically determine, for every input, the solution that is most effective for training the network parameters in any given learning iteration.
1 code implementation • 9 Jun 2020 • Rajas Bansal, Shreshth Tuli, Rohan Paul, Mausam
When compared to a graph neural network baseline, it achieves 14-27% accuracy improvement for predicting known tools from new world scenes, and 44-67% improvement in generalization for novel objects not encountered during training.
Robotics
1 code implementation • ACL 2020 • Keshav Kolluru, Samarth Aggarwal, Vipul Rathore, Mausam, Soumen Chakrabarti
While traditional systems for Open Information Extraction were statistical and rule-based, recently neural models have been introduced for the task.
1 code implementation • EMNLP 2020 • Prachi Jain, Sushant Rathi, Mausam, Soumen Chakrabarti
Temporal knowledge bases associate relational (s, r, o) triples with a set of times (or a single time instant) when the relation is valid.
Ranked #1 on Link Prediction on Wikidata12k
1 code implementation • 2 May 2020 • Prachi Jain, Sushant Rathi, Mausam, Soumen Chakrabarti
Most existing methods train with a small number of negative samples for each positive instance in these datasets to save computational costs.
1 code implementation • AKBC 2021 • Vaibhav Adlakha, Parth Shah, Srikanta Bedathur, Mausam
In response, we develop RotatE-Box -- a novel combination of RotatE and box embeddings.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Pratyush Maini, Keshav Kolluru, Danish Pruthi, Mausam
We find that pooling-based architectures substantially differ from their non-pooling equivalents in their learning ability and positional biases--which elucidate their performance benefits.
no code implementations • 30 Apr 2020 • Dinesh Raghu, Nikhil Gupta, Mausam
Task-oriented dialog (TOD) systems often need to formulate knowledge base (KB) queries corresponding to the user intent and use the query results to generate system responses.
no code implementations • EMNLP 2020 • Dirk Groeneveld, Tushar Khot, Mausam, Ashish Sabharwal
State-of-the-art models for multi-hop question answering typically augment large-scale language models like BERT with additional, intuitively useful capabilities such as named entity recognition, graph-based reasoning, and question decomposition.
Ranked #37 on Question Answering on HotpotQA
no code implementations • 18 Feb 2020 • Sankalp Garg, Aniket Bajpai, Mausam
We present SymNet, the first neural approach for solving RMDPs that are expressed in the probabilistic planning language of RDDL.
1 code implementation • AKBC 2020 • Yatin Nandwani, Ankesh Gupta, Aman Agrawal, Mayank Singh Chauhan, Parag Singla, Mausam
State-of-the-art models for Knowledge Base Completion (KBC) are based on tensor factorization (TF), e. g, DistMult, ComplEx.
1 code implementation • NeurIPS 2019 • Yatin Nandwani, Abhishek Pathak, Mausam, Parag Singla
In this paper, we present a constrained optimization formulation for training a deep network with a given set of hard constraints on output labels.
no code implementations • 8 Sep 2019 • Danish Contractor, Krunal Shah, Aditi Partap, Mausam, Parag Singla
We introduce the novel task of answering entity-seeking recommendation questions using a collection of reviews that describe candidate answer entities.
no code implementations • 8 Feb 2019 • Sankalp Garg, Aniket Bajpai, Mausam
To mitigate this, recent work has studied neural transfer learning, so that a generic planner trained on other problems of the same domain can rapidly transfer to a new problem.
1 code implementation • NeurIPS 2018 • Aniket Bajpai, Sankalp Garg, Mausam
We then learn an RL agent in the embedding space, making a near zero-shot transfer possible, i. e., without much training on the new instance, and without using the domain simulator at all.
1 code implementation • 2 Jul 2018 • Gagan Madan, Ankit Anand, Mausam, Parag Singla
These orbits are represented compactly using permutations over variables, and variable-value (VV) pairs, but they can miss several state symmetries in a domain.
1 code implementation • NAACL 2019 • Dinesh Raghu, Nikhil Gupta, Mausam
We also systematically modify existing datasets to measure disentanglement and show BoSsNet to be robust to KB modifications.
1 code implementation • 27 Jul 2017 • Ankit Anand, Ritesh Noothigattu, Parag Singla, Mausam
Moreover, algorithms for lifted inference in multi-valued domains also compute a multi-valued extension of count symmetries only.
1 code implementation • 22 Jul 2017 • Haroun Habeeb, Ankit Anand, Mausam, Parag Singla
We demonstrate the performance of C2F inference by developing lifted versions of two near state-of-the-art CV algorithms for stereo vision and interactive image segmentation.
2 code implementations • 2 Jun 2017 • Prachi Jain, Shikhar Murty, Mausam, Soumen Chakrabarti
If not, what characteristics of a dataset determine the performance of MF and TF models?
1 code implementation • 12 Feb 2017 • Karan Goel, Shreya Rajpal, Mausam
We present Octopus, an AI agent to jointly balance three conflicting task objectives on a micro-crowdsourcing marketplace - the quality of work, total cost incurred, and time to completion.
no code implementations • 31 Aug 2016 • Christopher H. Lin, Mausam, Daniel S. Weld
We present POAPS, a novel planning system for defining Partially Observable Markov Decision Processes (POMDPs) that abstracts away from POMDP details for the benefit of non-expert practitioners.
no code implementations • 30 Jun 2016 • Ankit Anand, Aditya Grover, Mausam, Parag Singla
We extend previous work on exploiting symmetries in the MCMC framework to the case of contextual symmetries.
no code implementations • 16 Jan 2014 • Peng Dai, Mausam, Daniel Sabby Weld, Judy Goldsmith
Value iteration is a powerful yet inefficient algorithm for Markov decision processes (MDPs) because it puts the majority of its effort into backing up the entire state space, which turns out to be unnecessary in many cases.
no code implementations • 15 Jan 2014 • Nicolas Meuleau, Emmanuel Benazera, Ronen I. Brafman, Eric A. Hansen, Mausam
We consider the problem of optimal planning in stochastic domains with resource constraints, where the resources are continuous and the choice of action at each step depends on resource availability.