Research Interest

My broad research interests are in Natural Language Processing, Human Computer Interaction and Deep Learning. Some of the areas I am working are,

Large Language Models Inference/Training and Representation Learning [ EMNLP-24 , EMNLP-23 , GEM@EMNLP-23 ]
Multi-granularity Information Extraction (event and argument extraction, argument augmentation) [ EMNLP-24 , AAAI-24, arXiv]
Multimodal NLP (analyze text, image, speech, and other meta signals to build intelligent systems and evaluate large VLMs) [ ACL-24 , EACL-24]
NLP for Social Good (application focusing on Social Science and Healthcare) [AAAI-24, ICWSM-24 , Neurocomputing]

Publications

To get the full list of my papers please check: [Google Scholar] / [Semantic Scholar]

Works in Progress

Large Language Models for Document-Level Event-Argument Data Augmentation for Challenging Role Types

Under Review

Socially Constructed Treatment Plans: Analyzing Online Peer Interactions to Understand How Patients Navigate Complex Medical Conditions

Under Review

Conferences

Explicit, Implicit, and Scattered: Revisiting Event Extraction to Capture Complex Arguments

Omar Sharif, Joseph Gatto, Madhusudan Basak, Sarah Preum
[EMNLP-2024] / [Paper] / [Dataset] / [Code] / [Talk] / [Slides] / [Project Website]

Characterizing Information Seeking Events in Health-Related Social Discourse

Omar Sharif, Madhusudan Basak, Tanzia Parvin, et al.
[AAAI-2024] / [Paper] / [Code] / [Dataset] / [Slides]

Deciphering Hate: Identifying Hateful Memes and Their Targets

Eftekhar Hossain, Omar Sharif, Mohammed Moshiul Hoque, Sarah Preum
[ACL-2024] / [Paper] / [Dataset & Code]

Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detection

Eftekhar Hossain*, Omar Sharif*, Mohammed Moshiul Hoque, Sarah Preum
[EACL-SRW-2024] / [Paper] / [Dataset & Code]

Chain-of-Thought Embeddings for Stance Detection on Social Media

Joseph Gatto, Omar Sharif, Sarah Preum
[EMNLP-2023 Findings] / [Paper] / [Code]

Text Encoders Lack Knowledge: Leveraging Generative LLMs for Domain-Specific Semantic Textual Similarity

Joseph Gatto, Omar Sharif, Parker Seegmiller, Philip Bohlman, Sarah Preum
[GEM@EMNLP-2023] / [Paper] / [Dataset] / [Slides]

Theme-driven Keyphrase Extraction to Analyze Social Media Discourse

William Romano*, Omar Sharif*, Madhusudan Basak, Joseph Gatto, Sarah Preum
[ICWSM-2024] / [Paper]

MUTE: A Multimodal Dataset for Detecting Hateful Memes

Eftekhar Hossain, Omar Sharif, Mohammed Moshiul Hoque
[AACL-SRW 2022] / [Paper]

M-BAD: A Multilabel Dataset for Detecting Aggressive Texts and Their Targets

Omar Sharif, Eftekhar Hossain, Mohammed Moshiul Hoque
[CONSTRAINT@ACL-2022] / [Paper]

Emotion Classification in a Resource Constrained Language Using Transformer-based Approach

Avishek Das, Omar Sharif, Mohammed Moshiul Hoque, Iqbal H. Sarker
[NAACL-SRW 2021] / [Paper] / [Code]

Align and Conquer: An Ensemble Approach to Classify Aggressive Texts from Social Media

Omar Sharif, Mohammed Moshiul Hoque
[SPICSCON-2021, IEEE] / [Paper]

Identification and Classification of Textual Aggression in Social Media: Resource Creation and Evaluation

🏆 [Best paper award (research track)]
Omar Sharif, Mohammed Moshiul Hoque
[CONSTRAINT@AAAI-2021 (acceptance rate: 37.1%)] / [Paper]

Sentiment analysis of Bengali texts on online restaurant reviews using multinomial Naïve Bayes

Omar Sharif, Mohammed Moshiul Hoque, Eftekhar Hossain
[ICASERT-2019, IEEE] / [Paper]

Automatic Detection of Suspicious Bangla Text Using Logistic Regression

Omar Sharif, Mohammed Moshiul Hoque
[ICO-2019, Springer] / [Paper]

Journals

Tackling Cyber-Aggression: Identification and Fine-Grained Categorization of Aggressive Texts on Social Media using Weighted Ensemble of Transformers

Omar Sharif, Mohammed Moshiul Hoque
[Neurocomputing (IF: 5.77, HI: 143)] / [Paper] / [Dataset]

Identification of Multilingual Offense and Troll from Social Media Memes using Weighted Ensemble of Multimodal Features

Eftekhar Hossain, Omar Sharif , Mohammed Moshiul Hoque, et al.
[JKSUCIS (IF: 8.83)] / [Paper]

Detecting Suspicious Texts Using Machine Learning Techniques

Omar Sharif, Mohammed Moshiul Hoque, A. S. M. Kayes, Raza Nowrozy, Iqbal H. Sarker
[Journal of Applied Sciences (IF: 2.67)] / [Paper]

Workshops

Multilingual Code-Mixed Hope Speech Detection using Cross-lingual Representation Learner

🥇 [Top model in multilingual hope speech detection challenge]
Eftekhar Hossain, Omar Sharif, Mohammed Moshiul Hoque
[LTEDI@EACL-2021] / [Paper] / [Code]

Offensive Language Detection from Multilingual Code-Mixed Text using Transformers

Omar Sharif, Eftekhar Hossain, Mohammed Moshiul Hoque
[DravidianLangTech@EACL-2021] / [Paper] / [Code]

Investigating Visual and Textual Features to Identify Trolls from Multimodal Social Media Memes

Eftekhar Hossain, Omar Sharif, Mohammed Moshiul Hoque
[DravidianLangTech@EACL-2021] / [Paper]

Combating Hostility: Covid-19 Fake News and Hostile Post Detection in Social Media

Omar Sharif, Eftekhar Hossain, Mohammed Moshiul Hoque
[Preprint@arXiv] / [Paper] / [Code]

TechTexC: Classification of Technical Texts using Convolution and Bidirectional Long Short Term Memory Network

Omar Sharif, Eftekhar Hossain, Mohammed Moshiul Hoque
[ICON-2020, ACL Indexed] / [Paper]

Others [Mentorship]

Some collaborative works with CUET NLP members were accepted in several conferences/ journals. However, my contribution to these works was <=25%. I performed a subset of these tasks: {Concpetualization, Verify implementation, Review and Edited draft manuscript}.

Word Embedding based Textual Semantic Similarity Measure in Bengali

MD. Asif Iqbal, Omar Sharif, Mohammed Moshiul Hoque, Iqbal H.Sarker
[Procedia Computer Science Journal] / [Paper]

Classification of Textual Sentiment Using Ensemble Technique

Md. Mashiur Rahaman Mamun, Omar Sharif, Mohammed Moshiul Hoque
[SN Computer Science Journal] / [Paper]

Multi-class Sports News Categorization using Machine Learning Techniques: Resource Creation and Evaluation

Adrita Barua, Omar Sharif, Mohammed Moshiul Hoque
[Procedia Computer Science Journal] / [Paper]

Automatic Categorization of News Articles and Headlines Using Multi-layer Perceptron

Fatima Jahara, Omar Sharif, Mohammed Moshiul Hoque
[ICO-2021, Springer] / [Paper]

BEmoD: Development of Bengali Emotion Dataset for Classifying Expressions of Emotion in Texts

Avishek Das, MD. Asif Iqbal, Omar Sharif, Mohammed Moshiul Hoque
[ICO-2020, Springer] / [Paper]

Towards POS Tagging Methods for Bengali Language: A Comparative Analysis

Fatima Jahara, Adrita Barua, MD. Asif Iqbal, Avishek Das, Omar Sharif, et al.
[ICO-2020, Springer] / [Paper]

An Empirical Framework for Bangla Word Sense Disambiguation Using Statistical Approach

Monisha Biswas, Omar Sharif, Mohammed Moshiul Hoque
[ICMLBDA-2021, Springer] / [Paper]

Fine-grained Categorization of Abusive Comments using Logistic Regression

Alamgir Hossain et al.,
[TamilNLP@ACL-22] / [Paper]

Exploiting Textual Features to Classify Sentiment of Multimodal Movie Reviews

Nasehatul Mustakim et al.,
[DravidianLang Tech@ACL-22] / [Paper]

Investigating Deep Learning Techniques to Detect Multimodal Troll Memes

Md Hasan et al.,
[DravidianLang Tech@ACL-22] / [Paper]

Multi-Class Textual Emotion Detection from Social Media using Transformer

Nasehatul Mustakim et al.,
[TamilNLP@ACL-22] / [Paper]