Search Results for author: Vasudeva Varma

Found 77 papers, 21 papers with code

IIIT-MLNS at SemEval-2022 Task 8: Siamese Architecture for Modeling Multilingual News Similarity

no code implementations SemEval (NAACL) 2022 Sagar Joshi, Dhaval Taunk, Vasudeva Varma

For modeling the similarity task by using the representations given by these models, a Siamese architecture was used as the underlying architecture.

Data Augmentation

An Ensemble Approach to Detect Emotions at an Essay Level

1 code implementation WASSA (ACL) 2022 Himanshu Maheshwari, Vasudeva Varma

This paper describes our system (IREL, reffered as himanshu. 1007 on Codalab) for Shared Task on Empathy Detection, Emotion Classification, and Personality Detection at 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis at ACL 2022.

Emotion Classification

IIITH at SemEval-2022 Task 5: A comparative study of deep learning models for identifying misogynous memes

no code implementations SemEval (NAACL) 2022 Tathagata Raha, Sagar Joshi, Vasudeva Varma

This paper provides a comparison of different deep learning methods for identifying misogynous memes for SemEval-2022 Task 5: Multimedia Automatic Misogyny Identification.

Can LLMs Generate Architectural Design Decisions? -An Exploratory Empirical study

no code implementations4 Mar 2024 Rudra Dhar, Karthik Vaidhyanathan, Vasudeva Varma

In our exploratory study, we utilize GPT and T5-based models with 0-shot, few-shot, and fine-tuning approaches to generate the Decision of an ADR given its Context.

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

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).

8k Classification +5

Summarizing Indian Languages using Multilingual Transformers based Models

no code implementations29 Mar 2023 Dhaval Taunk, Vasudeva Varma

With the advent of multilingual models like mBART, mT5, IndicBART etc., summarization in low resource Indian languages is getting a lot of attention now a days.

GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering

no code implementations22 Mar 2023 Dhaval Taunk, Lakshya Khanna, Pavan Kandru, Vasudeva Varma, Charu Sharma, Makarand Tapaswi

Commonsense question-answering (QA) methods combine the power of pre-trained Language Models (LM) with the reasoning provided by Knowledge Graphs (KG).

Common Sense Reasoning Knowledge Graphs +1

Massively Multilingual Language Models for Cross Lingual Fact Extraction from Low Resource Indian Languages

1 code implementation9 Feb 2023 Bhavyajeet Singh, Pavan Kandru, Anubhav Sharma, Vasudeva Varma

Cross Lingual Information Extraction aims at extracting factual information in the form of English triples from low resource Indian Language text.

Knowledge Graphs World Knowledge

Investigating Strategies for Clause Recommendation

1 code implementation21 Jan 2023 Sagar Joshi, Sumanth Balaji, Jerrin Thomas, Aparna Garimella, Vasudeva Varma

Clause recommendation is the problem of recommending a clause to a legal contract, given the context of the contract in question and the clause type to which the clause should belong.

Text Generation

Graph-based Keyword Planning for Legal Clause Generation from Topics

1 code implementation7 Jan 2023 Sagar Joshi, Sumanth Balaji, Aparna Garimella, Vasudeva Varma

Generating domain-specific content such as legal clauses based on minimal user-provided information can be of significant benefit in automating legal contract generation.

Text Generation

Gui at MixMT 2022 : English-Hinglish: An MT approach for translation of code mixed data

no code implementations21 Oct 2022 Akshat Gahoi, Jayant Duneja, Anshul Padhi, Shivam Mangale, Saransh Rajput, Tanvi Kamble, Dipti Misra Sharma, Vasudeva Varma

The first task dealt with both Roman and Devanagari script as we had monolingual data in both English and Hindi whereas the second task only had data in Roman script.

Translation Transliteration

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

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

Knowledge-based Extraction of Cause-Effect Relations from Biomedical Text

no code implementations10 Mar 2021 Sachin Pawar, Ravina More, Girish K. Palshikar, Pushpak Bhattacharyya, Vasudeva Varma

We propose a knowledge-based approach for extraction of Cause-Effect (CE) relations from biomedical text.

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

Task Adaptive Pretraining of Transformers for Hostility Detection

no code implementations9 Jan 2021 Tathagata Raha, Sayar Ghosh Roy, Ujwal Narayan, Zubair Abid, Vasudeva Varma

Identifying adverse and hostile content on the web and more particularly, on social media, has become a problem of paramount interest in recent years.

Binary Classification Classification +2

Leveraging Multilingual Transformers for Hate Speech Detection

1 code implementation8 Jan 2021 Sayar Ghosh Roy, Ujwal Narayan, Tathagata Raha, Zubair Abid, Vasudeva Varma

Our work leverages state of the art Transformer language models to identify hate speech in a multilingual setting.

feature selection General Classification +1

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

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

Adapting Language Models for Non-Parallel Author-Stylized Rewriting

no code implementations22 Sep 2019 Bakhtiyar Syed, Gaurav Verma, Balaji Vasan Srinivasan, Anandhavelu Natarajan, Vasudeva Varma

Given the recent progress in language modeling using Transformer-based neural models and an active interest in generating stylized text, we present an approach to leverage the generalization capabilities of a language model to rewrite an input text in a target author's style.

Denoising Language Modelling

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

Extraction of Message Sequence Charts from Software Use-Case Descriptions

no code implementations NAACL 2019 Girish Palshikar, Nitin Ramrakhiyani, Sangameshwar Patil, Sachin Pawar, Swapnil Hingmire, Vasudeva Varma, Pushpak Bhattacharyya

We apply this tool to extract MSCs from several real-life software use-case descriptions and show that it performs better than the existing techniques.

Extraction of Message Sequence Charts from Narrative History Text

no code implementations WS 2019 Girish Palshikar, Sachin Pawar, Sangameshwar Patil, Swapnil Hingmire, Nitin Ramrakhiyani, Harsimran Bedi, Pushpak Bhattacharyya, Vasudeva Varma

In this paper, we advocate the use of Message Sequence Chart (MSC) as a knowledge representation to capture and visualize multi-actor interactions and their temporal ordering.

Dependency Parsing

When science journalism meets artificial intelligence : An interactive demonstration

no code implementations EMNLP 2018 Raghuram Vadapalli, Bakhtiyar Syed, Nishant Prabhu, Balaji Vasan Srinivasan, Vasudeva Varma

We present an online interactive tool that generates titles of blog titles and thus take the first step toward automating science journalism.

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

SWDE : A Sub-Word And Document Embedding Based Engine for Clickbait Detection

no code implementations2 Aug 2018 Vaibhav Kumar, Mrinal Dhar, Dhruv Khattar, Yash Kumar Lal, Abhimanshu Mishra, Manish Shrivastava, Vasudeva Varma

We generate sub-word level embeddings of the title using Convolutional Neural Networks and use them to train a bidirectional LSTM architecture.

Clickbait Detection Document Embedding +1

ELDEN: Improved Entity Linking Using Densified Knowledge Graphs

1 code implementation NAACL 2018 Priya Radhakrishnan, Partha Talukdar, Vasudeva Varma

Entity Linking (EL) systems aim to automatically map mentions of an entity in text to the corresponding entity in a Knowledge Graph (KG).

Entity Disambiguation Entity Embeddings +2

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

Semi-Supervised Recurrent Neural Network for Adverse Drug Reaction Mention Extraction

no code implementations6 Sep 2017 Shashank Gupta, Sachin Pawar, Nitin Ramrakhiyani, Girish Palshikar, Vasudeva Varma

Current methods in ADR mention extraction relies on supervised learning methods, which suffers from labeled data scarcity problem.

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.

16k Event Extraction +3

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

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

Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text

3 code implementations COLING 2016 Ameya Prabhu, Aditya Joshi, Manish Shrivastava, Vasudeva Varma

We introduce a Hindi-English (Hi-En) code-mixed dataset for sentiment analysis and perform empirical analysis comparing the suitability and performance of various state-of-the-art SA methods in social media.

Opinion Mining Sentiment Analysis

Towards Deep Semantic Analysis Of Hashtags

no code implementations13 Jan 2015 Piyush Bansal, Romil Bansal, Vasudeva Varma

Hashtags are semantico-syntactic constructs used across various social networking and microblogging platforms to enable users to start a topic specific discussion or classify a post into a desired category.

Entity Linking Sentiment Analysis

Enrichment of Bilingual Dictionary through News Stream Data

no code implementations LREC 2014 Ajay Dubey, Parth Gupta, Vasudeva Varma, Paolo Rosso

Many time the language pair does not have large bilingual comparable corpora and in such cases the best automatic dictionary is upper bounded by the quality and coverage of such corpora.

Information Retrieval

Exploring the Role of Logically Related Non-Question Phrases for Answering Why-Questions

no code implementations29 Mar 2013 Niraj Kumar, Rashmi Gangadharaiah, Kannan Srinathan, Vasudeva Varma

Next, we apply an improved version of ranking with a prior-based approach, which ranks all words in the candidate document with respect to a set of root words (i. e. non-stopwords present in the question and in the candidate document).

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