no code implementations • ACL (ECNLP) 2021 • Mayank Jain, Sourangshu Bhattacharya, Harshit Jain, Karimulla Shaik, Muthusamy Chelliah
We perform detailed experiments to show that our method indeed increases the macro-F1 scores for attribute value extraction in general, and for labels with low training data in particular.
no code implementations • 8 Mar 2024 • Soumi Das, Shubhadip Nag, Shreyyash Sharma, Suparna Bhattacharya, Sourangshu Bhattacharya
In this work, we propose a controllable framework for data-centric trustworthy AI (DCTAI)- VTruST, that allows users to control the trade-offs between the different trustworthiness metrics of the constructed training datasets.
no code implementations • 26 Oct 2023 • Venktesh V, Sourangshu Bhattacharya, Avishek Anand
We transfer the ability to decompose complex questions to simpler questions or generate step-by-step rationales to LLMs, by careful selection from available data sources of related tasks.
no code implementations • 3 May 2023 • Kiran Purohit, Soumi Das, Sourangshu Bhattacharya, Santu Rana
We also show that LearnDefend is robust to size and noise in the marking of clean examples in the defense dataset.
1 code implementation • 23 Jun 2022 • Vinayak Gupta, Srikanta Bedathur, Sourangshu Bhattacharya, Abir De
In this work, we provide a novel unsupervised model and inference method for learning MTPP in presence of event sequences with missing events.
no code implementations • 14 Mar 2022 • Soumi Das, Manasvi Sagarkar, Suparna Bhattacharya, Sourangshu Bhattacharya
Another key contribution is the study of data valuation in the domain adaptation setting, where a data value estimator obtained using checkpoints from training trajectory in the source domain training dataset is used for data valuation in a target domain training dataset.
no code implementations • 5 Jan 2022 • Paramita Koley, Aurghya Maiti, Sourangshu Bhattacharya, Niloy Ganguly
On inspecting, we realize that an overall incentive scheme for the weak team does not incentivize the weaker agents within that team to learn and improve.
Multi-agent Reinforcement Learning reinforcement-learning +1
1 code implementation • 10 Dec 2021 • Rajdeep Mukherjee, Uppada Vishnu, Hari Chandana Peruri, Sourangshu Bhattacharya, Koustav Rudra, Pawan Goyal, Niloy Ganguly
Occurrences of catastrophes such as natural or man-made disasters trigger the spread of rumours over social media at a rapid pace.
1 code implementation • EMNLP 2021 • Rajdeep Mukherjee, Tapas Nayak, Yash Butala, Sourangshu Bhattacharya, Pawan Goyal
Aspect Sentiment Triplet Extraction (ASTE) deals with extracting opinion triplets, consisting of an opinion target or aspect, its associated sentiment, and the corresponding opinion term/span explaining the rationale behind the sentiment.
2 code implementations • 26 Aug 2021 • Sk Mainul Islam, Sourangshu Bhattacharya
We propose AR-BERT, a novel two-level global-local entity embedding scheme that allows efficient joint training of KG-based aspect embeddings and ALSC models.
Aspect-Based Sentiment Analysis (ABSA) Explanation Generation +3
1 code implementation • 28 Apr 2021 • Soumi Das, Arshdeep Singh, Saptarshi Chatterjee, Suparna Bhattacharya, Sourangshu Bhattacharya
In this paper, we study the problem of selecting high-value subsets of training data.
no code implementations • 24 Mar 2021 • Soumi Das, Harikrishna Patibandla, Suparna Bhattacharya, Kshounis Bera, Niloy Ganguly, Sourangshu Bhattacharya
We design a novel convex optimization-based multi-criteria online subset selection algorithm that uses a thresholded concave function of selection variables.
no code implementations • 11 Feb 2021 • Paramita Koley, Avirup Saha, Sourangshu Bhattacharya, Niloy Ganguly, Abir De
The networked opinion diffusion in online social networks (OSN) is often governed by the two genres of opinions - endogenous opinions that are driven by the influence of social contacts among users, and exogenous opinions which are formed by external effects like news, feeds etc.
no code implementations • ICCV 2021 • Soumi Das, Harikrishna Patibandla, Suparna Bhattacharya, Kshounis Bera, Niloy Ganguly, Sourangshu Bhattacharya
Training vision-based Autonomous driving models is a challenging problem with enormous practical implications.
no code implementations • 10 Jun 2020 • Haripriya Harikumar, Vuong Le, Santu Rana, Sourangshu Bhattacharya, Sunil Gupta, Svetha Venkatesh
Recently, it has been shown that deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch.
1 code implementation • 8 Jun 2020 • Rajdeep Mukherjee, Hari Chandana Peruri, Uppada Vishnu, Pawan Goyal, Sourangshu Bhattacharya, Niloy Ganguly
Manually extracting relevant aspects and opinions from large volumes of user-generated text is a time-consuming process.
no code implementations • 6 Nov 2019 • Soumi Das, Rajath Nandan Kalava, Kolli Kiran Kumar, Akhil Kandregula, Kalpam Suhaas, Sourangshu Bhattacharya, Niloy Ganguly
Travel time estimation is a fundamental problem in transportation science with extensive literature.
1 code implementation • 15 Jan 2018 • Chandan Misra, Sourangshu Bhattacharya, Soumya K. Ghosh
The growth of big data in domains such as Earth Sciences, Social Networks, Physical Sciences, etc.
Distributed, Parallel, and Cluster Computing
no code implementations • 6 Oct 2016 • Asis Roy, Sourangshu Bhattacharya, Kalyan Guin
Our objective is to devise a general methodology for customizing tests using user preferences so that expensive or uncomfortable tests can be avoided.
no code implementations • 30 Sep 2015 • Ayan Das, Sourangshu Bhattacharya
Experimental results on a variety of toy and real world datasets show that our approach is significantly more accurate than parameter averaging for high number of partitions.
no code implementations • NeurIPS 2007 • Mehul Parsana, Sourangshu Bhattacharya, Chiru Bhattacharya, K. Ramakrishnan
This paper introduces kernels on attributed pointsets, which are sets of vectors embedded in an euclidean space.