Search Results for author: Ramit Sawhney

Found 35 papers, 14 papers with code

A Risk-Averse Mechanism for Suicidality Assessment on Social Media

no code implementations ACL 2022 Ramit Sawhney, Atula Neerkaje, Manas Gaur

Recent studies have shown that social media has increasingly become a platform for users to express suicidal thoughts outside traditional clinical settings.

HYPHEN: Hyperbolic Hawkes Attention For Text Streams

1 code implementation ACL 2022 Shivam Agarwal, Ramit Sawhney, Sanchit Ahuja, Ritesh Soun, Sudheer Chava

Analyzing the temporal sequence of texts from sources such as social media, news, and parliamentary debates is a challenging problem as it exhibits time-varying scale-free properties and fine-grained timing irregularities.

Stock Price Prediction

DMix: Adaptive Distance-aware Interpolative Mixup

1 code implementation ACL 2022 Ramit Sawhney, Megh Thakkar, Shrey Pandit, Ritesh Soun, Di Jin, Diyi Yang, Lucie Flek

Interpolation-based regularisation methods such as Mixup, which generate virtual training samples, have proven to be effective for various tasks and modalities. We extend Mixup and propose DMix, an adaptive distance-aware interpolative Mixup that selects samples based on their diversity in the embedding space.

Data Augmentation Diversity +2

CIAug: Equipping Interpolative Augmentation with Curriculum Learning

1 code implementation NAACL 2022 Ramit Sawhney, Ritesh Soun, Shrey Pandit, Megh Thakkar, Sarvagya Malaviya, Yuval Pinter

CIAug achieves state-of-the-art results over existing interpolative augmentation methods on 10 benchmark datasets across 4 languages in text classification and named-entity recognition tasks.

Data Augmentation named-entity-recognition +5

A Time-Aware Transformer Based Model for Suicide Ideation Detection on Social Media

no code implementations EMNLP 2020 Ramit Sawhney, Harshit Joshi, Saumya Gandhi, Rajiv Ratn Shah

Understanding the build-up of such ideation is critical for the identification of at-risk users and suicide prevention.

VolTAGE: Volatility Forecasting via Text Audio Fusion with Graph Convolution Networks for Earnings Calls

1 code implementation EMNLP 2020 Ramit Sawhney, Piyush Khanna, Arshiya Aggarwal, Taru Jain, Puneet Mathur, Rajiv Ratn Shah

Natural language processing has recently made stock movement forecasting and volatility forecasting advances, leading to improved financial forecasting.

Deep Attentive Learning for Stock Movement Prediction From Social Media Text and Company Correlations

1 code implementation EMNLP 2020 Ramit Sawhney, Shivam Agarwal, Arnav Wadhwa, Rajiv Ratn Shah

In the financial domain, risk modeling and profit generation heavily rely on the sophisticated and intricate stock movement prediction task.

 Ranked #1 on Stock Market Prediction on stocknet (using extra training data)

Decision Making Graph Neural Network +1

HypMix: Hyperbolic Interpolative Data Augmentation

1 code implementation EMNLP 2021 Ramit Sawhney, Megh Thakkar, Shivam Agarwal, Di Jin, Diyi Yang, Lucie Flek

Interpolation-based regularisation methods for data augmentation have proven to be effective for various tasks and modalities.

Adversarial Robustness Data Augmentation

DocEdit-v2: Document Structure Editing Via Multimodal LLM Grounding

no code implementations21 Oct 2024 Manan Suri, Puneet Mathur, Franck Dernoncourt, Rajiv Jain, Vlad I Morariu, Ramit Sawhney, Preslav Nakov, Dinesh Manocha

Document structure editing involves manipulating localized textual, visual, and layout components in document images based on the user's requests.

How Much User Context Do We Need? Privacy by Design in Mental Health NLP Application

no code implementations5 Sep 2022 Ramit Sawhney, Atula Tejaswi Neerkaje, Ivan Habernal, Lucie Flek

Clinical NLP tasks such as mental health assessment from text, must take social constraints into account - the performance maximization must be constrained by the utmost importance of guaranteeing privacy of user data.

Cryptocurrency Bubble Detection: A New Stock Market Dataset, Financial Task & Hyperbolic Models

1 code implementation NAACL 2022 Ramit Sawhney, Shivam Agarwal, Vivek Mittal, Paolo Rosso, Vikram Nanda, Sudheer Chava

Further, we develop a set of sequence-to-sequence hyperbolic models suited to this multi-span identification task based on the power-law dynamics of cryptocurrencies and user behavior on social media.

The Impact of Differential Privacy on Group Disparity Mitigation

1 code implementation NAACL (PrivateNLP) 2022 Victor Petrén Bach Hansen, Atula Tejaswi Neerkaje, Ramit Sawhney, Lucie Flek, Anders Søgaard

The performance cost of differential privacy has, for some applications, been shown to be higher for minority groups; fairness, conversely, has been shown to disproportionally compromise the privacy of members of such groups.

Fairness

ADIMA: Abuse Detection In Multilingual Audio

1 code implementation16 Feb 2022 Vikram Gupta, Rini Sharon, Ramit Sawhney, Debdoot Mukherjee

Abusive content detection in spoken text can be addressed by performing Automatic Speech Recognition (ASR) and leveraging advancements in natural language processing.

Abuse Detection Automatic Speech Recognition +2

Multimodal Multi-Speaker Merger \& Acquisition Financial Modeling: A New Task, Dataset, and Neural Baselines

no code implementations ACL 2021 Ramit Sawhney, Mihir Goyal, Prakhar Goel, Puneet Mathur, Rajiv Ratn Shah

We introduce M3ANet, a baseline architecture that takes advantage of the multimodal multi-speaker input to forecast the financial risk associated with the M{\&}A calls.

Multitask Learning for Emotionally Analyzing Sexual Abuse Disclosures

1 code implementation NAACL 2021 Ramit Sawhney, Puneet Mathur, Taru Jain, Akash Kumar Gautam, Rajiv Ratn Shah

We show how for more domain-specific tasks related to sexual abuse disclosures such as sarcasm identification and dialogue act (refutation, justification, allegation) classification, homogeneous multitask learning is helpful, whereas for more general tasks such as stance and hate speech detection, heterogeneous multitask learning with emotion classification works better.

Classification Emotion Classification +2

Suicide Ideation Detection via Social and Temporal User Representations using Hyperbolic Learning

no code implementations NAACL 2021 Ramit Sawhney, Harshit Joshi, Rajiv Ratn Shah, Lucie Flek

Recent psychological studies indicate that individuals exhibiting suicidal ideation increasingly turn to social media rather than mental health practitioners.

An Empirical Investigation of Bias in the Multimodal Analysis of Financial Earnings Calls

1 code implementation NAACL 2021 Ramit Sawhney, Arshiya Aggarwal, Rajiv Ratn Shah

In this work, we present the first study to discover the gender bias in multimodal volatility prediction due to gender-sensitive audio features and fewer female executives in earnings calls of one of the world{'}s biggest stock indexes, the S{\&}P 500 index.

Quantitative Day Trading from Natural Language using Reinforcement Learning

no code implementations NAACL 2021 Ramit Sawhney, Arnav Wadhwa, Shivam Agarwal, Rajiv Ratn Shah

It is challenging to design profitable and practical trading strategies, as stock price movements are highly stochastic, and the market is heavily influenced by chaotic data across sources like news and social media.

reinforcement-learning Reinforcement Learning +2

FAST: Financial News and Tweet Based Time Aware Network for Stock Trading

no code implementations EACL 2021 Ramit Sawhney, Arnav Wadhwa, Shivam Agarwal, Rajiv Ratn Shah

Designing profitable trading strategies is complex as stock movements are highly stochastic; the market is influenced by large volumes of noisy data across diverse information sources like news and social media.

Learning-To-Rank

PHASE: Learning Emotional Phase-aware Representations for Suicide Ideation Detection on Social Media

1 code implementation EACL 2021 Ramit Sawhney, Harshit Joshi, Lucie Flek, Rajiv Ratn Shah

Building on clinical studies, PHASE learns phase-like progressions in users{'} historical Plutchik-wheel-based emotions to contextualize suicidal intent.

GPolS: A Contextual Graph-Based Language Model for Analyzing Parliamentary Debates and Political Cohesion

no code implementations COLING 2020 Ramit Sawhney, Arnav Wadhwa, Shivam Agarwal, Rajiv Ratn Shah

Parliamentary debates present a valuable language resource for analyzing comprehensive options in electing representatives under a functional, free society.

Language Modelling Sentiment Analysis

#MeTooMA: Multi-Aspect Annotations of Tweets Related to the MeToo Movement

no code implementations14 Dec 2019 Akash Gautam, Puneet Mathur, Rakesh Gosangi, Debanjan Mahata, Ramit Sawhney, Rajiv Ratn Shah

In this paper, we present a dataset containing 9, 973 tweets related to the MeToo movement that were manually annotated for five different linguistic aspects: relevance, stance, hate speech, sarcasm, and dialogue acts.

\#YouToo? Detection of Personal Recollections of Sexual Harassment on Social Media

1 code implementation ACL 2019 Arijit Ghosh Chowdhury, Ramit Sawhney, Rajiv Ratn Shah, Debanjan Mahata

The availability of large-scale online social data, coupled with computational methods can help us answer fundamental questions relat- ing to our social lives, particularly our health and well-being.

ARHNet - Leveraging Community Interaction for Detection of Religious Hate Speech in Arabic

no code implementations ACL 2019 Arijit Ghosh Chowdhury, Aniket Didolkar, Ramit Sawhney, Rajiv Ratn Shah

The rapid widespread of social media has lead to some undesirable consequences like the rapid increase of hateful content and offensive language.

Word Embeddings

Speak up, Fight Back! Detection of Social Media Disclosures of Sexual Harassment

no code implementations NAACL 2019 Arijit Ghosh Chowdhury, Ramit Sawhney, Puneet Mathur, Debanjan Mahata, Rajiv Ratn Shah

The {\#}MeToo movement is an ongoing prevalent phenomenon on social media aiming to demonstrate the frequency and widespread of sexual harassment by providing a platform to speak narrate personal experiences of such harassment.

Classification General Classification +4

Did you offend me? Classification of Offensive Tweets in Hinglish Language

1 code implementation WS 2018 Puneet Mathur, Ramit Sawhney, Meghna Ayyar, Rajiv Shah

The use of code-switched languages (\textit{e. g.}, Hinglish, which is derived by the blending of Hindi with the English language) is getting much popular on Twitter due to their ease of communication in native languages.

Abuse Detection General Classification +3

Exploring and Learning Suicidal Ideation Connotations on Social Media with Deep Learning

no code implementations WS 2018 Ramit Sawhney, Manch, Prachi a, Puneet Mathur, Rajiv Shah, Raj Singh

The increasing suicide rates amongst youth and its high correlation with suicidal ideation expression on social media warrants a deeper investigation into models for the detection of suicidal intent in text such as tweets to enable prevention.

Deep Learning General Classification +3

Detecting Offensive Tweets in Hindi-English Code-Switched Language

no code implementations WS 2018 Puneet Mathur, Rajiv Shah, Ramit Sawhney, Debanjan Mahata

The paper focuses on the classification of offensive tweets written in Hinglish language, which is a portmanteau of the Indic language Hindi with the Roman script.

General Classification Hate Speech Detection +1

A Computational Approach to Feature Extraction for Identification of Suicidal Ideation in Tweets

no code implementations ACL 2018 Ramit Sawhney, Manch, Prachi a, Raj Singh, Swati Aggarwal

Technological advancements in the World Wide Web and social networks in particular coupled with an increase in social media usage has led to a positive correlation between the exhibition of Suicidal ideation on websites such as Twitter and cases of suicide.

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