Search Results for author: Ashutosh Modi

Found 61 papers, 31 papers with code

IITK at SemEval-2024 Task 2: Exploring the Capabilities of LLMs for Safe Biomedical Natural Language Inference for Clinical Trials

1 code implementation6 Apr 2024 Shreyasi Mandal, Ashutosh Modi

Large Language models (LLMs) have demonstrated state-of-the-art performance in various natural language processing (NLP) tasks across multiple domains, yet they are prone to shortcut learning and factual inconsistencies.

Natural Language Inference Retrieval +1

EtiCor: Corpus for Analyzing LLMs for Etiquettes

1 code implementation29 Oct 2023 Ashutosh Dwivedi, Pradhyumna Lavania, Ashutosh Modi

Etiquettes are an essential ingredient of day-to-day interactions among people.

ISLTranslate: Dataset for Translating Indian Sign Language

1 code implementation11 Jul 2023 Abhinav Joshi, Susmit Agrawal, Ashutosh Modi

To the best of our knowledge, it is the largest translation dataset for continuous Indian Sign Language.

Sentence Sign Language Translation +1

U-CREAT: Unsupervised Case Retrieval using Events extrAcTion

1 code implementation11 Jul 2023 Abhinav Joshi, Akshat Sharma, Sai Kiran Tanikella, Ashutosh Modi

To further promote research in PCR, in this paper, we propose a new large benchmark (in English) for the PCR task: IL-PCR (Indian Legal Prior Case Retrieval) corpus.

Retrieval

ScriptWorld: Text Based Environment For Learning Procedural Knowledge

1 code implementation8 Jul 2023 Abhinav Joshi, Areeb Ahmad, Umang Pandey, Ashutosh Modi

Text-based games provide a framework for developing natural language understanding and commonsense knowledge about the world in reinforcement learning based agents.

Language Modelling Natural Language Understanding +1

SemEval 2023 Task 6: LegalEval - Understanding Legal Texts

no code implementations19 Apr 2023 Ashutosh Modi, Prathamesh Kalamkar, Saurabh Karn, Aman Tiwari, Abhinav Joshi, Sai Kiran Tanikella, Shouvik Kumar Guha, Sachin Malhan, Vivek Raghavan

LegalEval task has three sub-tasks: Task-A (Rhetorical Roles Labeling) is about automatically structuring legal documents into semantically coherent units, Task-B (Legal Named Entity Recognition) deals with identifying relevant entities in a legal document and Task-C (Court Judgement Prediction with Explanation) explores the possibility of automatically predicting the outcome of a legal case along with providing an explanation for the prediction.

named-entity-recognition Named Entity Recognition

Generalized Product-of-Experts for Learning Multimodal Representations in Noisy Environments

no code implementations7 Nov 2022 Abhinav Joshi, Naman Gupta, Jinang Shah, Binod Bhattarai, Ashutosh Modi, Danail Stoyanov

In order to process the multimodal information automatically and use it for an end application, Multimodal Representation Learning (MRL) has emerged as an active area of research in recent times.

3D Hand Pose Estimation Representation Learning +2

COGMEN: COntextualized GNN based Multimodal Emotion recognitioN

2 code implementations NAACL 2022 Abhinav Joshi, Ashwani Bhat, Ayush Jain, Atin Vikram Singh, Ashutosh Modi

Emotions are an inherent part of human interactions, and consequently, it is imperative to develop AI systems that understand and recognize human emotions.

Multimodal Emotion Recognition

Semantic Segmentation of Legal Documents via Rhetorical Roles

1 code implementation3 Dec 2021 Vijit Malik, Rishabh Sanjay, Shouvik Kumar Guha, Angshuman Hazarika, Shubham Nigam, Arnab Bhattacharya, Ashutosh Modi

For automatically segmenting the legal documents, we experiment with the task of rhetorical role prediction: given a document, predict the text segments corresponding to various roles.

Semantic Segmentation

BreakingBERT@IITK at SemEval-2021 Task 9: Statement Verification and Evidence Finding with Tables

no code implementations SEMEVAL 2021 Aditya Jindal, Ankur Gupta, Jaya Srivastava, Preeti Menghwani, Vijit Malik, Vishesh Kaushik, Ashutosh Modi

There are two subtasks, in which given a table and a statement/fact, the subtask A is to determine whether the statement is inferred from the tabular data and the subtask B is to determine which cells in the table provide evidence for the former subtask.

Fact Verification Natural Language Inference

IITK at SemEval-2021 Task 10: Source-Free Unsupervised Domain Adaptation using Class Prototypes

no code implementations SEMEVAL 2021 Harshit Kumar, Jinang Shah, Nidhi Hegde, Priyanshu Gupta, Vaibhav Jindal, Ashutosh Modi

To tackle this issue of availability of annotated data, a lot of research has been done on unsupervised domain adaptation that tries to generate systems for an unlabelled target domain data, given labeled source domain data.

Data Augmentation Negation +3

Fine-Grained Emotion Prediction by Modeling Emotion Definitions

1 code implementation26 Jul 2021 Gargi Singh, Dhanajit Brahma, Piyush Rai, Ashutosh Modi

In this paper, we propose a new framework for fine-grained emotion prediction in the text through emotion definition modeling.

Language Modelling Masked Language Modeling +1

Pre-trained Language Models as Prior Knowledge for Playing Text-based Games

1 code implementation18 Jul 2021 Ishika Singh, Gargi Singh, Ashutosh Modi

Given the sample-inefficiency of RL approaches, it is inefficient to learn rich enough textual representations to be able to understand and reason using the textual observation in such a complicated game environment setting.

text-based games

NLP for Climate Policy: Creating a Knowledge Platform for Holistic and Effective Climate Action

no code implementations12 May 2021 Pradip Swarnakar, Ashutosh Modi

We investigate the opinions (sentiments) of major actors' narratives towards climate policy in the second methodology.

BreakingBERT@IITK at SemEval-2021 Task 9 : Statement Verification and Evidence Finding with Tables

1 code implementation7 Apr 2021 Aditya Jindal, Ankur Gupta, Jaya Srivastava, Preeti Menghwani, Vijit Malik, Vishesh Kaushik, Ashutosh Modi

Given a table and a statement/fact, subtask A determines whether the statement is inferred from the tabular data, and subtask B determines which cells in the table provide evidence for the former subtask.

Fact Verification Natural Language Inference

KnowGraph@IITK at SemEval-2021 Task 11: Building KnowledgeGraph for NLP Research

1 code implementation4 Apr 2021 Shashank Shailabh, Sajal Chaurasia, Ashutosh Modi

Finding relevant research papers and their contribution to the domain is a challenging problem.

ReCAM@IITK at SemEval-2021 Task 4: BERT and ALBERT based Ensemble for Abstract Word Prediction

1 code implementation SEMEVAL 2021 Abhishek Mittal, Ashutosh Modi

We fine-tuned the pre-trained masked language models namely BERT and ALBERT and used an Ensemble of these as our submitted system on Subtask 1 (ReCAM-Imperceptibility) and Subtask 2 (ReCAM-Nonspecificity).

Language Modelling Masked Language Modeling +1

An End-to-End Network for Emotion-Cause Pair Extraction

1 code implementation2 Mar 2021 Aaditya Singh, Shreeshail Hingane, Saim Wani, Ashutosh Modi

The task of Emotion-Cause Pair Extraction (ECPE) aims to extract all potential clause-pairs of emotions and their corresponding causes in a document.

Emotion Cause Extraction Emotion-Cause Pair Extraction

Adv-OLM: Generating Textual Adversaries via OLM

1 code implementation EACL 2021 Vijit Malik, Ashwani Bhat, Ashutosh Modi

Analysis of these attacks on the state of the art transformers in NLP can help improve the robustness of these models against such adversarial inputs.

Sentence text-classification +1

Adapting a Language Model for Controlled Affective Text Generation

1 code implementation COLING 2020 Ishika Singh, Ahsan Barkati, Tushar Goswamy, Ashutosh Modi

The model gives a user the flexibility to control the category and intensity of emotion as well as the topic of the generated text.

Language Modelling Text Generation

AI-based Monitoring and Response System for Hospital Preparedness towards COVID-19 in Southeast Asia

no code implementations30 Jul 2020 Tushar Goswamy, Naishadh Parmar, Ayush Gupta, Raunak Shah, Vatsalya Tandon, Varun Goyal, Sanyog Gupta, Karishma Laud, Shivam Gupta, Sudhanshu Mishra, Ashutosh Modi

This research paper proposes a COVID-19 monitoring and response system to identify the surge in the volume of patients at hospitals and shortage of critical equipment like ventilators in South-east Asian countries, to understand the burden on health facilities.

BAKSA at SemEval-2020 Task 9: Bolstering CNN with Self-Attention for Sentiment Analysis of Code Mixed Text

1 code implementation SEMEVAL 2020 Ayush Kumar, Harsh Agarwal, Keshav Bansal, Ashutosh Modi

Sentiment Analysis of code-mixed text has diversified applications in opinion mining ranging from tagging user reviews to identifying social or political sentiments of a sub-population.

General Classification Opinion Mining +1

problemConquero at SemEval-2020 Task 12: Transformer and Soft label-based approaches

1 code implementation SEMEVAL 2020 Karishma Laud, Jagriti Singh, Randeep Kumar Sahu, Ashutosh Modi

We submitted two models for sub-task C (offense target identification), one using soft labels and the other using BERT based fine-tuned model.

Language Identification

newsSweeper at SemEval-2020 Task 11: Context-Aware Rich Feature Representations For Propaganda Classification

1 code implementation SEMEVAL 2020 Paramansh Singh, Siraj Sandhu, Subham Kumar, Ashutosh Modi

This paper describes our submissions to SemEval 2020 Task 11: Detection of Propaganda Techniques in News Articles for each of the two subtasks of Span Identification and Technique Classification.

Classification General Classification +4

IITK at SemEval-2020 Task 10: Transformers for Emphasis Selection

1 code implementation SEMEVAL 2020 Vipul Singhal, Sahil Dhull, Rishabh Agarwal, Ashutosh Modi

This paper describes the system proposed for addressing the research problem posed in Task 10 of SemEval-2020: Emphasis Selection For Written Text in Visual Media.

Domain Authoring Assistant for Intelligent Virtual Agents

no code implementations5 Apr 2019 Sepehr Janghorbani, Ashutosh Modi, Jakob Buhmann, Mubbasir Kapadia

The process of creating such characters often involves a team of creative authors who describe different aspects of the characters in natural language, and planning experts that translate this description into a planning domain.

Affect-Driven Dialog Generation

no code implementations NAACL 2019 Pierre Colombo, Wojciech Witon, Ashutosh Modi, James Kennedy, Mubbasir Kapadia

The majority of current systems for end-to-end dialog generation focus on response quality without an explicit control over the affective content of the responses.

Topic Spotting using Hierarchical Networks with Self Attention

no code implementations NAACL 2019 Pooja Chitkara, Ashutosh Modi, Pravalika Avvaru, Sepehr Janghorbani, Mubbasir Kapadia

Additionally, in contrast to offline processing of dialog, we also analyze the performance of our model in a more realistic setting i. e. in an online setting where the topic is identified in real time as the dialog progresses.

text-classification Text Classification

MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge

no code implementations LREC 2018 Simon Ostermann, Ashutosh Modi, Michael Roth, Stefan Thater, Manfred Pinkal

We introduce a large dataset of narrative texts and questions about these texts, intended to be used in a machine comprehension task that requires reasoning using commonsense knowledge.

Natural Language Understanding Reading Comprehension

A Mixture Model for Learning Multi-Sense Word Embeddings

no code implementations SEMEVAL 2017 Dai Quoc Nguyen, Dat Quoc Nguyen, Ashutosh Modi, Stefan Thater, Manfred Pinkal

Our model generalizes the previous works in that it allows to induce different weights of different senses of a word.

Word Embeddings

Learning Semantic Script Knowledge with Event Embeddings

no code implementations18 Dec 2013 Ashutosh Modi, Ivan Titov

Induction of common sense knowledge about prototypical sequences of events has recently received much attention.

Common Sense Reasoning

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