Pinned Repositories
ArabicMMLU
Artist-Identification-CNN
This project tackles the issue of artist identification from paintings. The aim is to accurately identify the artist of a painting using transfer learning by training different Convolutional Neural Networks (CNNs) with varying Residual Networks (ResNet).
Audio-Data-Pre-Processing
biosbias
Code to reproduce data for Bias in Bios
dialex
DiaLex - A Benchmark for Evaluating Multidialectal Arabic Word Embeddings
donut
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
Gender-Bias-Datasets-Lexicons
Language has a profound impact on our thoughts, perceptions, and conceptions of gender roles. Gender-inclusive language is, therefore, a key tool to promote social inclusion and contribute to achieving gender equality. Consequently, detecting and mitigating gender bias in texts is instrumental in halting its propagation and societal implications. However, there is a lack of gender bias datasets and lexicons for automating the detection of gender bias using supervised and unsupervised machine learning (ML) and natural language processing (NLP) techniques. Therefore, the main contribution of this work is to publicly provide labeled datasets and exhaustive lexicons by collecting, annotating, and augmenting relevant sentences to facilitate the detection of gender bias in English text. Towards this end, we present an updated version of our previously proposed taxonomy by re-formalizing its structure, adding a new bias type, and mapping each bias subtype to an appropriate detection methodology. The released datasets and lexicons span multiple bias subtypes including: Generic He, Generic She, Explicit Marking of Sex, and Gendered Neologisms. We leveraged the use of word embedding models to further augment the collected lexicons. The underlying motivation of our work is to enable the technical community to combat gender bias in text and halt its propagation using ML and NLP techniques.
Gender_Generalization
Gender Generalization Bias
Google-Search-Scrapper
Multiprocessing-Tesseract-4.0
In an effort to decrease the execution time of the OCR process, a multi-processing script was created using Python's multi-processing module.
jaddoughman's Repositories
jaddoughman/Multiprocessing-Tesseract-4.0
In an effort to decrease the execution time of the OCR process, a multi-processing script was created using Python's multi-processing module.
jaddoughman/Gender-Bias-Datasets-Lexicons
Language has a profound impact on our thoughts, perceptions, and conceptions of gender roles. Gender-inclusive language is, therefore, a key tool to promote social inclusion and contribute to achieving gender equality. Consequently, detecting and mitigating gender bias in texts is instrumental in halting its propagation and societal implications. However, there is a lack of gender bias datasets and lexicons for automating the detection of gender bias using supervised and unsupervised machine learning (ML) and natural language processing (NLP) techniques. Therefore, the main contribution of this work is to publicly provide labeled datasets and exhaustive lexicons by collecting, annotating, and augmenting relevant sentences to facilitate the detection of gender bias in English text. Towards this end, we present an updated version of our previously proposed taxonomy by re-formalizing its structure, adding a new bias type, and mapping each bias subtype to an appropriate detection methodology. The released datasets and lexicons span multiple bias subtypes including: Generic He, Generic She, Explicit Marking of Sex, and Gendered Neologisms. We leveraged the use of word embedding models to further augment the collected lexicons. The underlying motivation of our work is to enable the technical community to combat gender bias in text and halt its propagation using ML and NLP techniques.
jaddoughman/Artist-Identification-CNN
This project tackles the issue of artist identification from paintings. The aim is to accurately identify the artist of a painting using transfer learning by training different Convolutional Neural Networks (CNNs) with varying Residual Networks (ResNet).
jaddoughman/ArabicMMLU
jaddoughman/Audio-Data-Pre-Processing
jaddoughman/biosbias
Code to reproduce data for Bias in Bios
jaddoughman/dialex
DiaLex - A Benchmark for Evaluating Multidialectal Arabic Word Embeddings
jaddoughman/donut
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
jaddoughman/Gender_Generalization
Gender Generalization Bias
jaddoughman/Google-Search-Scrapper
jaddoughman/Image-Segmentation
Segmentation algorithm that uses Google's Tesseract 4.0 OCR engine to segment an image into its contained areas, paragraphs, lines, or words.
jaddoughman/interspeech-2019
Interspeech 2019 experiments
jaddoughman/nougat
Implementation of Nougat Neural Optical Understanding for Academic Documents
jaddoughman/PyChatGPT
⚡️ Python client for the unofficial ChatGPT API with auto token regeneration, conversation tracking, proxy support and more.
jaddoughman/quora-scraper
Scrape data from Quora website: questions related to certain topics, answers given on certain questions and users profile data
jaddoughman/sec-web-scraper-13f
Python Web scraper for parsing 13F filings (mutual fund holdings) from SEC website
jaddoughman/spark-cassandra-connector
Spark Cassandra Connector
jaddoughman/Team-Slot
Web application for organizing team meetings through multi-user calendar overlap and scheduling links. The goals was to produce a visually appealing web application that would revive human connection through efficiently generated team or individual meetings.
jaddoughman/tesseract
Tesseract Open Source OCR Engine (main repository)