no code implementations • COLING 2022 • Subba Reddy Oota, Jashn Arora, Manish Gupta, Raju S. Bapi
(2) Our extensive analysis across 9 broad regions, 11 language sub-regions and 16 visual sub-regions of the brain help us localize, for the first time, the parts of the brain involved in cross-view tasks like image captioning, image tagging, sentence formation and keyword extraction.
no code implementations • 23 Dec 2023 • Ankita Maity, Anubhav Sharma, Rudra Dhar, Tushar Abhishek, Manish Gupta, Vasudeva Varma
Next, we investigate the effectiveness of popular multilingual Transformer-based models for the two tasks by modeling detection as a binary classification problem and mitigation as a style transfer problem.
no code implementations • 13 Dec 2023 • Nitin Agarwal, Ashish Kumar, Kiran R, Manish Gupta, Laurent Boué
Azure Cognitive Search (ACS) has emerged as a major contender in "Search as a Service" cloud products in recent years.
no code implementations • 28 Jul 2023 • Kaushal Kumar Maurya, Maunendra Sankar Desarkar, Manish Gupta, Puneet Agrawal
However, such NLG models suffer from two drawbacks: (1) some of the previous session queries could be noisy and irrelevant to the user intent for the current prefix, and (2) NLG models cannot directly incorporate historical query popularity.
no code implementations • 17 Jul 2023 • Subba Reddy Oota, Manish Gupta, Raju S. Bapi, Gael Jobard, Frederic Alexandre, Xavier Hinaut
In this survey, we will first discuss popular representations of language, vision and speech stimuli, and present a summary of neuroscience datasets.
no code implementations • 29 Jun 2023 • Abhirama Subramanyam Penamakuri, Manish Gupta, Mithun Das Gupta, Anand Mishra
We study visual question answering in a setting where the answer has to be mined from a pool of relevant and irrelevant images given as a context.
1 code implementation • 15 Jun 2023 • Tathagata Raha, Mukund Choudhary, Abhinav Menon, Harshit Gupta, KV Aditya Srivatsa, Manish Gupta, Vasudeva Varma
The proposed system first predicts inconsistent spans from claim and context; and then uses them to predict inconsistency types and inconsistent entity types (when inconsistency is due to entities).
1 code implementation • 24 May 2023 • Bishal Santra, Sakya Basak, Abhinandan De, Manish Gupta, Pawan Goyal
The research contributes to a better understanding of how LLMs can be effectively used for building interactive systems.
1 code implementation • 23 May 2023 • Pavan Kalyan Reddy Neerudu, Subba Reddy Oota, Mounika Marreddy, Venkateswara Rao Kagita, Manish Gupta
Further, how robust are these models to perturbations in input text?
1 code implementation • 6 May 2023 • Mithun Das, Rohit Raj, Punyajoy Saha, Binny Mathew, Manish Gupta, Animesh Mukherjee
Hate speech has become one of the most significant issues in modern society, having implications in both the online and the offline world.
1 code implementation • 22 Mar 2023 • Dhaval Taunk, Shivprasad Sagare, Anupam Patil, Shivansh Subramanian, Manish Gupta, Vasudeva Varma
But, for low-resource languages, the scarcity of reference articles makes monolingual summarization ineffective in solving this problem.
Ranked #1 on Cross-Lingual Abstractive Summarization on XWikiRef
Cross-Lingual Abstractive Summarization Document Summarization +3
no code implementations • 9 Mar 2023 • Satarupa Guha, Rahul Ambavat, Ankur Gupta, Manish Gupta, Rupeshkumar Mehta
However, WER fails to provide a fair evaluation of human perceived quality in presence of spelling variations, abbreviations, or compound words arising out of agglutination.
no code implementations • 16 Feb 2023 • Subba Reddy Oota, Mounika Marreddy, Manish Gupta, Bapi Raju Surampud
In this study, we investigate the predictive power of the brain encoding models in three settings: (i) individual performance of the constituency and dependency syntactic parsing based embedding methods, (ii) efficacy of these syntactic parsing based embedding methods when controlling for basic syntactic signals, (iii) relative effectiveness of each of the syntactic embedding methods when controlling for the other.
1 code implementation • 31 Dec 2022 • Sayar Ghosh Roy, Anshul Padhi, Risubh Jain, Manish Gupta, Vasudeva Varma
We model sentence-specific popularity forecasting as a sequence regression task.
no code implementations • 22 Sep 2022 • Shivprasad Sagare, Tushar Abhishek, Bhavyajeet Singh, Anubhav Sharma, Manish Gupta, Vasudeva Varma
Our extensive experiments show that a multi-lingual mT5 model which uses fact-aware embeddings with structure-aware input encoding leads to best results on average across the twelve languages.
Ranked #1 on Data-to-Text Generation on XAlign
no code implementations • 21 May 2022 • Bishal Santra, Ravi Ghadia, Manish Gupta, Pawan Goyal
Furthermore, CE loss computation for the dialog generation task does not take the input context into consideration and, hence, it grades the response irrespective of the context.
no code implementations • NAACL 2022 • Subba Reddy Oota, Jashn Arora, Veeral Agarwal, Mounika Marreddy, Manish Gupta, Bapi Raju Surampudi
Several popular Transformer based language models have been found to be successful for text-driven brain encoding.
no code implementations • COLING 2022 • Subba Reddy Oota, Jashn Arora, Vijay Rowtula, Manish Gupta, Raju S. Bapi
In this paper, we systematically explore the efficacy of image Transformers (ViT, DEiT, and BEiT) and multi-modal Transformers (VisualBERT, LXMERT, and CLIP) for brain encoding.
no code implementations • 18 Apr 2022 • Subba Reddy Oota, Jashn Arora, Manish Gupta, Raju S. Bapi
Also, the decoded representations are sufficiently detailed to enable high accuracy for cross-view-translation tasks with following pairwise accuracy: IC (78. 0), IT (83. 0), KE (83. 7) and SF (74. 5).
no code implementations • NeurIPS Workshop DBAI 2021 • Nic Jedema, Thuy Vu, Manish Gupta, Alessandro Moschitti
While transformers demonstrate impressive performance on many knowledge intensive (KI) tasks, their ability to serve as implicit knowledge bases (KBs) remains limited, as shown on several slot-filling, question-answering (QA), fact verification, and entity-linking tasks.
no code implementations • 8 Feb 2022 • Pranay Gupta, Manish Gupta
Answering questions in the context of videos can be helpful in video indexing, video retrieval systems, video summarization, learning management systems and surveillance video analysis.
1 code implementation • 1 Feb 2022 • Tushar Abhishek, Shivprasad Sagare, Bhavyajeet Singh, Anubhav Sharma, Manish Gupta, Vasudeva Varma
Multiple critical scenarios (like Wikipedia text generation given English Infoboxes) need automated generation of descriptive text in low resource (LR) languages from English fact triples.
Ranked #3 on Data-to-Text Generation on XAlign
no code implementations • NAACL 2022 • Bishal Santra, Sumegh Roychowdhury, Aishik Mandal, Vasu Gurram, Atharva Naik, Manish Gupta, Pawan Goyal
Although many pretrained models exist for text or images, there have been relatively fewer attempts to train representations specifically for dialog understanding.
2 code implementations • 5 Sep 2021 • Tushar Abhishek, Daksh Rawat, Manish Gupta, Vasudeva Varma
Coherence is an important aspect of text quality and is crucial for ensuring its readability.
Ranked #1 on Coherence Evaluation on GCDC + RST - Accuracy
1 code implementation • CVPR 2022 • Kushal Chauhan, Barath Mohan U, Pradeep Shenoy, Manish Gupta, Devarajan Sridharan
Likelihoods computed by deep generative models (DGMs) are a candidate metric for outlier detection with unlabeled data.
1 code implementation • 13 Apr 2021 • Mohit Chandra, Dheeraj Pailla, Himanshu Bhatia, AadilMehdi Sanchawala, Manish Gupta, Manish Shrivastava, Ponnurangam Kumaraguru
Hence, we collect and label two datasets with 3, 102 and 3, 509 social media posts from Twitter and Gab respectively.
1 code implementation • 10 Jan 2021 • Sayar Ghosh Roy, Nikhil Pinnaparaju, Risubh Jain, Manish Gupta, Vasudeva Varma
Traditionally, various feature engineering and machine learning based systems have been proposed for extractive as well as abstractive text summarization.
Ranked #2 on Extended Summarization on Longsumm Blind Test
1 code implementation • 18 Dec 2020 • Omkar Gurjar, Manish Gupta
Using a dataset of 2000 reviews related to 1000 tourist spots, our broad level classifier provides a binary overlap F1 of $\sim$80 and $\sim$82 to classify a phrase as inclusion or exclusion respectively.
no code implementations • COLING 2020 • Vijayasaradhi Indurthi, Bakhtiyar Syed, Manish Gupta, Vasudeva Varma
It is not only essential to identify a click-bait, but also to identify the intensity of the clickbait based on the strength of the clickbait.
1 code implementation • IEEE Cloud Computing in Emerging Markets 2020 • Pranav Gupta, Manish Gupta
Can we have a way to understand the risk of a person being infected as compared to another person so that we can make decisions of segregating the two people or to decline entry to a person?
1 code implementation • COLING 2020 • Mohit Chandra, Ashwin Pathak, Eesha Dutta, Paryul Jain, Manish Gupta, Manish Shrivastava, Ponnurangam Kumaraguru
While extensive popularity of online social media platforms has made information dissemination faster, it has also resulted in widespread online abuse of different types like hate speech, offensive language, sexist and racist opinions, etc.
1 code implementation • 12 Aug 2020 • Manish Gupta, Puneet Agrawal
In recent years, the fields of natural language processing (NLP) and information retrieval (IR) have made tremendous progress thanksto deep learning models like Recurrent Neural Networks (RNNs), Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTMs)networks, and Transformer [120] based models like Bidirectional Encoder Representations from Transformers (BERT) [24], GenerativePre-training Transformer (GPT-2) [94], Multi-task Deep Neural Network (MT-DNN) [73], Extra-Long Network (XLNet) [134], Text-to-text transfer transformer (T5) [95], T-NLG [98] and GShard [63].
no code implementations • 15 Jan 2020 • Pinkesh Badjatiya, Manish Gupta, Vasudeva Varma
Knowledge-based generalization provides an effective way to encode knowledge because the abstraction they provide not only generalizes content but also facilitates retraction of information from the hate speech detection classifier, thereby reducing the imbalance.
no code implementations • 25 Dec 2019 • Abhishek Kumar Singh, Manish Gupta, Vasudeva Varma
While the conventional approaches rely on human crafted document-independent features to generate a summary, we develop a data-driven novel summary system called HNet, which exploits the various semantic and compositional aspects latent in a sentence to capture document independent features.
no code implementations • 25 Dec 2019 • Abhishek Kumar Singh, Manish Gupta, Vasudeva Varma
Extractive text summarization has been an extensive research problem in the field of natural language understanding.
1 code implementation • IJCNLP 2019 • Pulkit Parikh, Harika Abburi, Pinkesh Badjatiya, Radhika Krishnan, Niyati Chhaya, Manish Gupta, Vasudeva Varma
Sexism, an injustice that subjects women and girls to enormous suffering, manifests in blatant as well as subtle ways.
no code implementations • SEMEVAL 2019 • Vijayasaradhi Indurthi, Bakhtiyar Syed, Manish Shrivastava, Manish Gupta, Vasudeva Varma
This paper describes our system (Fermi) for Task 6: OffensEval: Identifying and Categorizing Offensive Language in Social Media of SemEval-2019.
no code implementations • SEMEVAL 2019 • Bakhtiyar Syed, Vijayasaradhi Indurthi, Manish Shrivastava, Manish Gupta, Vasudeva Varma
This information is highly useful in segregating factual questions from non-factual ones which highly helps in organizing the questions into useful categories and trims down the problem space for the next task in the pipeline for fact evaluation among the available answers.
no code implementations • SEMEVAL 2019 • Vijayasaradhi Indurthi, Bakhtiyar Syed, Manish Shrivastava, Nikhil Chakravartula, Manish Gupta, Vasudeva Varma
This paper describes our system (Fermi) for Task 5 of SemEval-2019: HatEval: Multilingual Detection of Hate Speech Against Immigrants and Women on Twitter.
no code implementations • 12 Mar 2019 • Indraneil Paul, Abhinav Khattar, Shaan Chopra, Ponnurangam Kumaraguru, Manish Gupta
The aim of the paper is two-fold: First, we test if discerning the verification status of a handle from profile metadata and content features is feasible.
1 code implementation • 29 Aug 2018 • Pinkesh Badjatiya, Litton J Kurisinkel, Manish Gupta, Vasudeva Varma
Text segmentation plays an important role in various Natural Language Processing (NLP) tasks like summarization, context understanding, document indexing and document noise removal.
no code implementations • 18 Feb 2018 • Madhav Nimishakavi, Bamdev Mishra, Manish Gupta, Partha Talukdar
Besides the tensors, in many real world scenarios, side information is also available in the form of matrices which also grow in size with time.
no code implementations • 14 Feb 2018 • Shashank Gupta, Manish Gupta, Vasudeva Varma, Sachin Pawar, Nitin Ramrakhiyani, Girish K. Palshikar
Adverse drug reactions (ADRs) are one of the leading causes of mortality in health care.
no code implementations • 14 Feb 2018 • Shashank Gupta, Manish Gupta, Vasudeva Varma, Sachin Pawar, Nitin Ramrakhiyani, Girish K. Palshikar
Adverse drug reactions (ADRs) are one of the leading causes of mortality in health care.
1 code implementation • 11 Nov 2017 • Supriya Pandhre, Himangi Mittal, Manish Gupta, Vineeth N. Balasubramanian
In this paper, we present a novel approach, STWalk, for learning trajectory representations of nodes in temporal graphs.
no code implementations • IJCNLP 2017 • Raghuram Vadapalli, Litton J Kurisinkel, Manish Gupta, Vasudeva Varma
Ideally a metric evaluating an abstract system summary should represent the extent to which the system-generated summary approximates the semantic inference conceived by the reader using a human-written reference summary.
Abstractive Text Summarization Natural Language Inference +2
1 code implementation • 1 Jun 2017 • Pinkesh Badjatiya, Shashank Gupta, Manish Gupta, Vasudeva Varma
Hate speech detection on Twitter is critical for applications like controversial event extraction, building AI chatterbots, content recommendation, and sentiment analysis.
1 code implementation • 4 Apr 2017 • J Ganesh, Manish Gupta, Vasudeva Varma
Research in analysis of microblogging platforms is experiencing a renewed surge with a large number of works applying representation learning models for applications like sentiment analysis, semantic textual similarity computation, hashtag prediction, etc.
2 code implementations • 30 Dec 2016 • Supriya Pandhre, Manish Gupta, Vineeth N. Balasubramanian
Although various kinds of outliers have been studied for graph data, there is not much work on anomaly detection from edge-attributed graphs.
Social and Information Networks G.2; G.3; H.2.8
1 code implementation • 19 Dec 2016 • Ganesh J, Manish Gupta, Vasudeva Varma
In this work we propose a novel representation learning model which computes semantic representations for tweets accurately.
1 code implementation • 15 Nov 2016 • J Ganesh, Manish Gupta, Vasudeva Varma
Research in social media analysis is experiencing a recent surge with a large number of works applying representation learning models to solve high-level syntactico-semantic tasks such as sentiment analysis, semantic textual similarity computation, hashtag prediction and so on.