Question-Answering Systems NLP Tools

Datasets, benchmarks, and frameworks for building question answering systems across modalities (open-domain, reading comprehension, commonsense, multilingual). Does NOT include general machine translation, information retrieval, or dialogue systems.

There are 65 question-answering systems tools tracked. 1 score above 50 (established tier). The highest-rated is PaddlePaddle/RocketQA at 54/100 with 785 stars and 22 monthly downloads.

Get all 65 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=nlp&subcategory=question-answering-systems&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	PaddlePaddle/RocketQA 🚀 RocketQA, dense retrieval for information retrieval and question...	54	Established	785	Python
2	allenai/deep_qa A deep NLP library, based on Keras / tf, focused on question answering (but...	44	Emerging	405	Python
3	worldbank/iQual iQual is a package that leverages natural language processing to scale up...	44	Emerging	25	Jupyter Notebook
4	shuaihuaiyi/QA 使用深度学习算法实现的中文问答系统	44	Emerging	557	Python
5	seriousran/awesome-qa 😎 A curated list of the Question Answering (QA)	40	Emerging	768	—
6	fhamborg/Giveme5W1H Extraction of the journalistic five W and one H questions (5W1H) from news...	40	Emerging	530	HTML
7	mandarjoshi90/triviaqa Code for the TriviaQA reading comprehension dataset	38	Emerging	332	Python
8	programmer290399/pyqna A simple python package for question answering.	38	Emerging	11	Python
9	huggingface/node-question-answering Fast and production-ready question answering in Node.js	37	Emerging	466	TypeScript
10	TheHamkerCat/python-arq Asynchronous Python Wrapper For A.R.Q API.	37	Emerging	37	Python
11	21han/nlp_qa_project Natural Language Processing Question Answering Final Project	37	Emerging	61	HTML
12	Karthik-Bhaskar/Context-Based-Question-Answering Context-Based-Question-Answering	35	Emerging	44	JavaScript
13	UKP-SQuARE/square-core SQuARE: Software for question answering research.	35	Emerging	75	Python
14	seominjoon/denspi Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index (DenSPI)	35	Emerging	200	Python
15	TmaxEdu/KorDPR This repo Implements "Dense Passage Retrieval for Open-Domain Question...	35	Emerging	75	Python
16	allenai/semanticilp Question Answering as Global Reasoning over Semantic Abstractions (AAAI-18)	34	Emerging	33	Scala
17	dice-group/TeBaQA A question answering system which utilises machine learning.	34	Emerging	21	Java
18	neuml/tldrstory 📊 Semantic search for headlines and story text	33	Emerging	359	Python
19	BDBC-KG-NLP/QA-Survey-CN 北京航空航天大学大数据高精尖中心自然语言处理研究团队开展了智能问答的研究与应用总结。包括基于知识图谱的问答（KBQA），基于文本的问答系统（TextQA）...	33	Emerging	1,812	—
20	CogComp/multirc Reasoning over Multiple Sentences (Multi-RC)	33	Emerging	34	Perl
21	ARBML/qawafi Platform for Arabic Poetry Analysis using knowledge-based and deep learning...	33	Emerging	36	Jupyter Notebook
22	apple/ml-mkqa We introduce MKQA, an open-domain question answering evaluation set...	33	Emerging	192	Python
23	Chia-Hsuan-Lee/KaggleDBQA Introduction page of a challenging text-to-SQL dataset: KaggleDBQA	30	Emerging	43	—
24	anassinator/markov-sentence-correction Markov Chains and Hidden Markov Models to generate and correct sentences	30	Emerging	21	Python
25	IBM/sciqa-arcade198-dataset ARCADE198 Dataset from the ACL 2018 MRQA Workshop	30	Emerging	15	—
26	soco-ai/SF-QA Evaluation framework for open-domain question answering.	30	Emerging	20	Python
27	stanford-oval/schema2qa Schema2QA Question Answering Dataset	27	Experimental	19	Makefile
28	AskNowQA/QA-Tutorial The repo contains all the materials related to Question Answering.	27	Experimental	47	—
29	RDTvlokip/InfiniQA The Official InfiniQA Dataset 📁📝	26	Experimental	3	Python
30	Mukhopadhyay/Amazon_QnA_Dataset Amazon question/answer dataset.	26	Experimental	7	—
31	siddharthkhincha/Inter-IIT-11-Devrev IIT Guwahati's Gold Medal winning solution to DevRev’s Expert Answers in a...	25	Experimental	10	Jupyter Notebook
32	pln-fing-udelar/newsqa-es Code to rebuild the NewsQA-es dataset: a Spanish version of the NewsQA dataset	23	Experimental	2	Python
33	I-QA-UCT/IQA Extensions to Yuan et al. QAit task.	23	Experimental	2	Python
34	scruel/campusQA Deeplearning4J框架搭建的第一个问答小AI	23	Experimental	11	Java
35	google-research-datasets/query-wellformedness 25,100 queries from the Paralex corpus (Fader et al., 2013) annotated with...	23	Experimental	85	—
36	hasanhuz/MentalQA MentalQA: An Annotated Arabic Corpus for Questions and Answers of Mental Healthcare	23	Experimental	6	—
37	christianbitter/QA_and_QG An inventory of data sets around Question Generation and Question Answering	22	Experimental	21	—
38	boostcampaitech3/level2-mrc-level2-nlp-09 네이버 부스트캠프 \| Open-Domain Question Answering(ODQA)	21	Experimental	6	Jupyter Notebook
39	Chia-Hsuan-Lee/ODSQA ODSQA: OPEN-DOMAIN SPOKEN QUESTION ANSWERING DATASET	21	Experimental	63	Shell
40	di37/question-answering-api-llm Question Answering System API based on all of the Harry Potter Books that...	21	Experimental	13	Python
41	boostcampaitech3/final-project-level3-nlp-09 네이버 부스트캠프 \| 회의록을 활용한 Closed-Domain Question Answering(CDQA)	20	Experimental	8	Jupyter Notebook
42	reddrex/lingcomp_QA An Spanish computational linguistics QA corpus (JSON format) with 1004 rows	19	Experimental	—	Jupyter Notebook
43	donderom/sqwat TUI editor for the Stanford Question Answering Dataset (SQuAD) 💬	19	Experimental	—	Go
44	ZhiyunLab/CsQA CommonsenseQA	19	Experimental	10	—
45	youngerous/Open-domain-QA Presentation slides of ODQA	19	Experimental	9	—
46	boostcampaitech2/mrc-level2-nlp-09 [2nd] KLUE Open-Domain Question Answering	19	Experimental	1	Jupyter Notebook
47	louisowen6/quora_paraphrasing_id Quora Paraphrasing Dataset Bahasa Indonesia Version	18	Experimental	11	Python
48	spapicchio/QATCH Official implementation of QATCH: Benchmarking SQL-centric tasks with Table...	18	Experimental	32	Python
49	AkariAsai/unanswerable_qa The official implementation for ACL 2021 "Challenges in Information Seeking...	16	Experimental	28	Python
50	orsiluk/Answer-Ranking Model to find relevant answers to questions on CQA (Community Question...	16	Experimental	4	Python
51	SockAndSandal/semantic-search-qa Code for the Semantic Search QA Algorithm	15	Experimental	2	Python
52	Dalia-Mahmoud-ElSayes/Gp-2022-ma3aref-Arabic-QA Our Graduation project: "Ma'aref" an Arabic Question Answering on Quran and Fatwa.	15	Experimental	2	Jupyter Notebook
53	Wikidepia/SQuAD-id Stanford Question Answering Dataset Translated to Indonesia.	15	Experimental	6	—
54	Sparshjain25/SQuAD-2.0 NLP Team 12	15	Experimental	1	Jupyter Notebook
55	motazsaad/Quran-QA Quran QA	14	Experimental	7	Jupyter Notebook
56	gsh199449/productqa Product-Aware Answer Generation in E-Commerce Question-Answering	14	Experimental	38	—
57	santhoshtr/wq An experimental natural language based querying system for Wikipedia	14	Experimental	11	Python
58	asaparov/fictionalgeoqa Question-answering dataset to evaluate reasoning ability over short paragraphs.	13	Experimental	7	Python
59	svjack/tableQA-Chinese Unsupervised tableQA and databaseQA on chinese finance question and tabular data	12	Experimental	13	Jupyter Notebook
60	ASoleimaniB/NLQuAD NLQuAD: A Non-Factoid Long Question Answering Data Set. To be published at EACL2021	12	Experimental	13	Python
61	aklein4/ASKiT Stanford CS224N Final Project. A text-based multi-hop reasoning...	12	Experimental	3	Python
62	mkearney/infoquality Information Quality	11	Experimental	2	Python
63	felixgiov/UDST-DurationQA Dataset from the paper "Improving Event Duration Question Answering by...	10	Experimental	1	—
64	GUT-AI/qa Question Answering (QA)	10	Experimental	1	—
65	lucadiliello/asnq-challenging ASNQ without trivial negative answers.	10	Experimental	1	Python