no code implementations • INLG (ACL) 2021 • Joy Mahapatra, Utpal Garain
The effectiveness of the proposed encoder is evaluated both extrinsically and intrinsically by shuffling input data without changing meaning of that data.
no code implementations • 30 Jan 2024 • Rahul Shah, Soumadeep Saha, Purba Mukherjee, Utpal Garain, Supratik Pal
We investigate the prospect of reconstructing the ``cosmic distance ladder'' of the Universe using a novel deep learning framework called LADDER - Learning Algorithm for Deep Distance Estimation and Reconstruction.
no code implementations • 20 Dec 2023 • Neeraj Kumar Singh, Koyel Ghosh, Joy Mahapatra, Utpal Garain, Apurbalal Senapati
We masked the 50\% hateful words of the comments identified as hateful and predicted the alternative words for these masked terms to generate convincing sentences.
2 code implementations • 21 Nov 2023 • Soumadeep Saha, Saptarshi Saha, Utpal Garain
In order to address this, we present the VALUE (Vision And Logical Understanding Evaluation) Dataset, consisting of 200, 000$+$ annotated images and an associated rule set, based on the popular board game - chess.
no code implementations • 20 Oct 2023 • Aditya Shankar Pal, Debojyoti Biswas, Joy Mahapatra, Debasis Banerjee, Prantar Chakrabarti, Utpal Garain
However, the capability of deep learning models to explain their WBC classification remains largely unexplored.
no code implementations • 9 Aug 2023 • Soumadeep Saha, Utpal Garain, Arijit Ukil, Arpan Pal, Sundeep Khandelwal
The enormous demand for annotated data brought forth by deep learning techniques has been accompanied by the problem of annotation noise.
1 code implementation • 21 Dec 2022 • Akshay Chaturvedi, Swarnadeep Bhar, Soumadeep Saha, Utpal Garain, Nicholas Asher
While transformer models achieve high performance on standard question answering tasks, we show that they fail to be semantically faithful once we perform these interventions for a significant number of cases (~50% for deletion intervention, and ~20% drop in accuracy for negation intervention).
1 code implementation • 5 Jun 2020 • Omid Mohamad Nezami, Akshay Chaturvedi, Mark Dras, Utpal Garain
We specifically aim to attack the widely used Faster R-CNN by changing the predicted label for a particular object in an image: where prior work has targeted one specific object (a stop sign), we generalise to arbitrary objects, with the key challenge being the need to change the labels of all bounding boxes for all instances of that object type.
no code implementations • 3 Aug 2019 • Akshay Chaturvedi, Abijith KP, Utpal Garain
In this paper, we study the behaviour of NMT systems when multiple changes are made to the source sentence.
1 code implementation • 11 Jun 2019 • Akshay Chaturvedi, Utpal Garain
Keeping this in mind, we propose Mimic and Fool, a task agnostic adversarial attack.
1 code implementation • 20 Aug 2018 • Anabik Pal, Akshay Chaturvedi, Utpal Garain, Aditi Chandra, Raghunath Chatterjee, Swapan Senapati
This paper presents an approach for automatic detection of Munro's Microabscess in stratum corneum (SC) of human skin biopsy in order to realize a machine assisted diagnosis of Psoriasis.
1 code implementation • 24 Jul 2018 • Anabik Pal, Sounak Ray, Utpal Garain
In this paper, a deep neural network based ensemble method is experimented for automatic identification of skin disease from dermoscopic images.
1 code implementation • ACL 2018 • Akshay Chaturvedi, P, Onkar it, Utpal Garain
The task of Question Answering is at the very core of machine comprehension.
no code implementations • 13 Jul 2017 • Snehasis Banerjee, Tanushyam Chattopadhyay, Arpan Pal, Utpal Garain
Several pattern recognition principles and state of art (SoA) ML techniques are followed to design the overall approach for the proposed automation.
no code implementations • ACL 2017 • Abhisek Chakrabarty, P, Onkar Arun it, Utpal Garain
It is found that except Bengali, the proposed method outperforms Lemming and Morfette on the other languages.
1 code implementation • 17 Dec 2016 • Snehasis Banerjee, Tanushyam Chattopadhyay, Swagata Biswas, Rohan Banerjee, Anirban Dutta Choudhury, Arpan Pal, Utpal Garain
In this paper, a Wide Learning architecture is proposed that attempts to automate the feature engineering portion of the machine learning (ML) pipeline.
no code implementations • LREC 2016 • Abhisek Chakrabarty, Akshay Chaturvedi, Utpal Garain
Given a word along with its contextual neighbours as input, the model is designed to produce the lemma of the concerned word as output.
no code implementations • 29 Sep 2014 • Arjun Das, Utpal Garain
NER in Bengali and Hindi finds accuracy (F measure) of 87% and 79%, respectively.
no code implementations • 2 Jan 2014 • Ankush Roy, Biswajit Halder, Utpal Garain, David S. Doermann
Real forensic samples are involved in the experiment that shows a high precision machine can be developed for authentication of paper money.