Asma Adala's repositories
allennlp
An open-source NLP research library, built on PyTorch.
data-cleaning-101
Data Cleaning Libraries with Python
datasets
A repository of pretty cool datasets that I collected for network science and machine learning research.
doc2vec
Text classification using Doc2Vec
efficientnet
Implementation of EfficientNet model. Keras and TensorFlow Keras.
fastai
The fastai deep learning library, plus lessons and and tutorials
fastText
Library for fast text representation and classification.
flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
keras-yolo3
Training and Detecting Objects with YOLO3
libpostal
A C library for parsing/normalizing street addresses around the world. Powered by statistical NLP and open geo data.
Machine_Learning
Some fundamental machine learning and data-analysis techniques are revisited here.
ml-models
Machine Learning Procedures and Functions for Neo4j
NER-datasets
Datasets to train supervised classifiers for Named-Entity Recognition
news-graph
Key information extraction from text and graph visualization
news-please
news-please - an integrated web crawler and information extractor for news that just works.
NLP-progress
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
nlp_highlights
The most important NLP highlights of 2018 (PDF Report)
pdf2htmlEX
Convert PDF to HTML without losing text or format.
pdftotree
:evergreen_tree: A tool for parsing PDF documents into a hierarchical, HTML-like tree.
PracticalMachineLearning
My ML related stuff including notebooks, codes and a curated list of various useful resources such as books and softwares. Almost everything mentioned here is free(as speech not free food) or open-source.
qalsadi
Qalsadi: Arabic mophological analyzer Library for python.
science-parse
Science Parse parses scientific papers (in PDF form) and returns them in structured form.
StarSpace
Learning embeddings for classification, retrieval and ranking.
tabula-java
Extract tables from PDF files
traprange
A Method to Extract Table Content in PDF Files (Java)
udify
A single model to parse Universal Dependencies across all languages.
udpipe
UDPipe: Trainable pipeline for tokenizing, tagging, lemmatizing and parsing Universal Treebanks and other CoNLL-U files
UDPipe-Future
CoNLL 2018 Shared Task Team UDPipe-Future
ulmfit-multilingual
Temporary repository used for collaboration on application of for multiple languages.