Projects I Worked On
Projects
Exploring Data Imbalance and Modality Bias in Hateful Memes
2021-04-14
Multi-modal memes which consist of an image and text are very popular on social media but can sometimes be intentionally or unintentionally hateful. Understanding them and if they are hateful frequently requires to consider image and text jointly. Naturally, hateful memes appear less frequent than non-hateful ones, creating a data imbalance in addition to modality biases present between the language and visual modality. In this work, we study the Hateful Memes dataset and evaluate several approaches to reduce data imbalance. In our experiments we show that simple dataset balancing and image augmentation can reduce the most concerning error, namely overlooking hateful content, significantly (175 to 112 errors), at a slight increase of overall accuracy.
Natural Language Processing in Ethiopian Languages: Current State, Challenges, and Opportunities
2023-03-25
This survey delves into the current state of natural language processing (NLP) for four Ethiopian languages: Amharic, Afaan Oromo, Tigrinya, and Wolaytta. Through this paper, we identify key challenges and opportunities for NLP research in Ethiopia. Furthermore, we provide a centralized repository on GitHub that contains publicly available resources for various NLP tasks in these languages. This repository can be updated periodically with contributions from other researchers. Our objective is to identify research gaps and disseminate the information to NLP researchers interested in Ethiopian languages and encourage future research in this domain.
Plant Disease Detection using Deep Learning
2021-03-10
Train and Evaluate different DNN Models for plant disease detection problem
To tackle the problem of scarce real-life representative data, experiment with different generative networks and generate more plant leaf image data
Implement segmentation pipeline to avoid misclassification due to unwanted inputAmharic Online Handwriting Recognition
2023-03-25
Using the touch screen capabilities of handhelds input method which is similar to handwriting is the best way to replace the current text entry approach. most people learn writing by using a pen and a pencil not a keyboard so writing on a touchscreen device like you write on a piece of paper is the natural and easiest way for the users .users can stroke their hand on a given canvas and the application reads what they write . Online handwriting recognition (OHWR) is getting renewed interest as it provides data entry mechanism that is similar to natural way of writing. This project mainly focuses on using this technique to solve the problem mentioned above. The online handwriting recognition project is not new idea .in recent years many researchers are adopting this method for their language use.