Discover qcri/dialectID Open Source project by QCRI (@qcri)

Benchmarking Large Language Models

LLMeBench

ArabicASRChallenge2016

This repository

Repository for performing Blocking using Deep Learning based on the paper "Deep Learning for Blocking in Entity Matching: A Design Space Exploration"

DeepBlocker

FarasaSegmenter

This code is part of the paper ''A Large Scale Benchmark to Validate Sleep-Wake Scoring Algorithms'' currently under review.

sleep_awake_benchmark

A python API for exposing and processing RDF data from sparql endpoints for data mining and machine learning models in convenient formats like Pandas dataframes.

dialectal_arabic_resources

Shell

RDFframes

Tasrif is a python library for processing of wearable data from fitness trackers and wearable health devices

tasrif

Passive DNS Dataset of Domain Resolutions

dialectal_arabic_tools

Roff

PDNS-Net

The first Dialectal Arabic Code Switching - DACS corpus from broadcast speech. Annotated at the token-level, considering both the linguistic and the acoustic cues. This dataset is a potential benchmark for DCS in spontaneous speech.

Arabic_speech_code_switching

dialectal_arabic_segmenter

Arabic Dialects Segmenter Using Keras/BiLSTM/ChainCRF

ArabicSpellChecker

QARiB

QLFactChecking

e-wer

Word Error Rate Estimation

data_civilizer_system

JavaScript

dialectal_arabic_pos_tagger

CoClean: Collaborative Data Cleaning

coclean

Arabic emotion recognition using deep neural networks

deepemotion

Cross-Modal Data Discovery over Structured and Unstructured Data Lakes

CMDL

multiRefWER

The Data Civilizer end-to-end data preparation system - 2.0

datacivilizer2

JavaScript

Kunafa

A python script using perf and PMU to monitor memory bandwidth, cache, and other performance metrics

Repository containing implementation for the ICDE 2022 paper "Accelerating Entity Lookups in Knowledge Graphs Through Embeddings"

EmbLookup

QCRI Arabic Dialect Identification

QADI

EvaluationMetrics

Code to evaluate cqa runs in the ECML 2016 challenge on reranking questions in community question answering

OpenAI Gym environment used in the KDD2019 Paper "Time Critic Policy Gradient Methods for Traffic Signal Control in Complex and Congested Scenarios"

gym-gharrafa

Segmenter of dialectal Arabic developed by QCRI, ALT team and published in EACL 2017 and CONLL 2017

qcri-svm-segmenter

PLSQL

DiplomaticPulse

Cross-language English-Arabic corpus derived from WikiQA

WikiQAar

RetClean

AI for Data Preparation

ALT research group publications

alt_public

TeX

alt-hackathon-docs

QCRI Speech Recognition and Machine Translation API's for Hackathons

JavaScript

PropagandaTechniquesAnalysisBERT

A System for Diacritizing Four Varieties of Arabic

dial-diac

CSS

cmuqhack2017

repository for cmu-q hackathon 2017

Real time map creation and update using gps data

gpsmap

tacotron2

QCRI Live News Demonstration

QLN-LiveNewsDemo

PHP

apihub

serve and publish API

COVID19 Themed Domain Blacklist

COVID19-MAL-Blacklist

dbcopier

Ruby tool to copy a database of any type to a database of any other type

Ruby

dockerized_moses_server

Dockerfile

ArabicSpeechTextProcessing

Processing Dialectal Arabic Speech Transcription

QCAI-TransportaionGroup-TrImpute

Deep Arabic Dialect Detection

deepdialect

PHD Data collect by Matheus Araujo

PHD_Datasets

qcri-demo-icassp-2018-client

The client side of QCRI demo at ICASSP 2018

CSS

RDF-generator

Converting structured and semi-structured data into RDF graphs.

GTI: Graph Trajectory Imputation

QCAI-TransportaionGroup-GTI

flight2vec

Boeing flight2vec project

HTML

Zagel

Chatting app based on the crosscloud platform

CSS

Arabesque-Skeleton

Skeleton template for new projects on top of Arabesque

TrafQ is a collection of Open AI environments and baseline algorithms for Traffic Light control optimization with Reinforcement Learning. Environments simulate real road networks and traffic.

TrafQ

Offline reinforcement learning for traffic signal control

ADAC-traffic

compromised

Detecting Compromised and Attack domains