husseinmozannar/SOQAL
Arabic Open Domain Question Answering System using Neural Reading Comprehension
Implements a two-stage retrieval-and-reading pipeline combining hierarchical TF-IDF document retrieval with multilingual BERT for span extraction. Introduces ARCD, a crowdsourced Arabic reading comprehension dataset of 1,395 Wikipedia-based questions, alongside Arabic-SQuAD with 48,344 machine-translated examples to address the scarcity of Arabic QA benchmarks.
165 stars. No commits in the last 6 months.
Stars
165
Forks
33
Language
Python
License
MIT
Category
Last pushed
Aug 04, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/husseinmozannar/SOQAL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
5hirish/adam_qas
ADAM - A Question Answering System. Inspired from IBM Watson
SatyamSoni23/Smart-Question-Answering-System-on-Document
It's Smart-Question Answering System on short as well as long documents. It can automatically...
dharmendrach/bert_quora_question_pairs
BERT Model Fine-tuning on Quora Questions Pairs
Chia-Hsuan-Lee/Spoken-SQuAD
A spoken question answering dataset on SQUAD
nocoolsandwich/iamQA
中文wiki百科QA阅读理解问答系统，使用了CCKS2016数据的NER模型和CMRC2018的阅读理解模型，还有W2V词向量搜索,使用torchserve部署