Search Results for author: Manish Gupta

Found 53 papers, 24 papers with code

Multi-view and Cross-view Brain Decoding

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.

Brain Decoding Image Captioning +2

Multilingual Bias Detection and Mitigation for Indian Languages

no code implementations23 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.

Bias Detection Binary Classification +1

Improving search relevance of Azure Cognitive Search by Bayesian optimization

no code implementations13 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.

Bayesian Optimization

Trie-NLG: Trie Context Augmentation to Improve Personalized Query Auto-Completion for Short and Unseen Prefixes

no code implementations28 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.

Text Generation

Deep Neural Networks and Brain Alignment: Brain Encoding and Decoding (Survey)

no code implementations17 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.

Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering

no code implementations29 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.

Answer Generation Question Answering +2

Neural models for Factual Inconsistency Classification with Explanations

1 code implementation15 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).

Classification Language Modelling +4

Frugal Prompting for Dialog Models

1 code implementation24 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.

HateMM: A Multi-Modal Dataset for Hate Video Classification

1 code implementation6 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.

Classification Hate Speech Detection +1

Unsupervised Language agnostic WER Standardization

no code implementations9 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.

speech-recognition Speech Recognition +1

Syntactic Structure Processing in the Brain while Listening

no code implementations16 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.

Activity Prediction Dependency Parsing +1

XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages

no code implementations22 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.

Data-to-Text Generation Descriptive +1

CORAL: Contextual Response Retrievability Loss Function for Training Dialog Generation Models

no code implementations21 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.

Reinforcement Learning (RL) Text Generation +1

Visio-Linguistic 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.

Cross-view Brain Decoding

no code implementations18 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).

Brain Decoding Image Captioning +4

DP-KB: Data Programming with Knowledge Bases Improves Transformer Fine Tuning for Answer Sentence Selection

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.

Entity Linking Fact Verification +4

NEWSKVQA: Knowledge-Aware News Video Question Answering

no code implementations8 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.

Common Sense Reasoning Management +7

XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages

1 code implementation1 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.

Data-to-Text Generation Descriptive

Robust outlier detection by de-biasing VAE likelihoods

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.

Outlier Detection

Summaformers @ LaySumm 20, LongSumm 20

1 code implementation10 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.

Abstractive Text Summarization Feature Engineering

Should I visit this place? Inclusion and Exclusion Phrase Mining from Reviews

1 code implementation18 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.

Sentiment Analysis

Predicting Clickbait Strength in Online Social Media

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.

Binary Classification

Managing Congregations of People by Predicting Likelihood of a Person being Infected by a Contagious Disease like the COVID Virus

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?

AbuseAnalyzer: Abuse Detection, Severity and Target Prediction for Gab Posts

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.

Abuse Detection severity prediction

Compression of Deep Learning Models for Text: A Survey

1 code implementation12 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].

Information Retrieval Knowledge Distillation +3

Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizations

no code implementations15 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.

Hate Speech Detection

Unity in Diversity: Learning Distributed Heterogeneous Sentence Representation for Extractive Summarization

no code implementations25 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.

Extractive Summarization Extractive Text Summarization +3

Hybrid MemNet for Extractive Summarization

no code implementations25 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.

Document Summarization Extractive Summarization +2

Fermi at SemEval-2019 Task 8: An elementary but effective approach to Question Discernment in Community QA Forums

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.

Community Question Answering Sentence

What sets Verified Users apart? Insights, Analysis and Prediction of Verified Users on Twitter

no code implementations12 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.

Attention-based Neural Text Segmentation

1 code implementation29 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.

Feature Engineering Segmentation +3

Inductive Framework for Multi-Aspect Streaming Tensor Completion with Side Information

no code implementations18 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.

STWalk: Learning Trajectory Representations in Temporal Graphs

1 code implementation11 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.

Change Point Detection Outlier Detection

SSAS: Semantic Similarity for Abstractive Summarization

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

Deep Learning for Hate Speech Detection in Tweets

1 code implementation1 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.

Event Extraction Hate Speech Detection +2

Interpretation of Semantic Tweet Representations

1 code implementation4 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.

Feature Engineering Property Prediction +3

Community-based Outlier Detection for Edge-attributed Graphs

2 code implementations30 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

Improving Tweet Representations using Temporal and User Context

1 code implementation19 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.

Representation Learning

Interpreting the Syntactic and Social Elements of the Tweet Representations via Elementary Property Prediction Tasks

1 code implementation15 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.

Property Prediction Representation Learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.