English»Software»Natural Language Processing & Information Extraction»Question Answering (QA) | searchivarius.org
log in | about 

Question generation

Slot filling


ADAM   - a Question Answering System. Inspired from IBM Watson
Aqqu   - More Accurate Question Answering on Freebase
Brmson  Petr Baudis - a Watson-like QA system. YodaQA is the main component.
BuboQA   - Retrieval-based model for simple question answering
cdQA   - An End-To-End Closed Domain Question Answering System.
deep_qa   - A deep NLP library, based on Keras / tf, focused on question answering (but useful for other NLP too).
DrQA   - a PyTorch implementation of the DrQA system described in the ACL 2017 paper Reading Wikipedia to Answer Open-Domain Questions.
Haystack   - neural QA at scale.
Jacana  Xuchen Yao - an NLP package for Question Answering and Monolingual Alignment
Jack the Reader   - a neural machine comprehension framework.
Jimmy Lin's collections   - Various software and data sets, including MIT Aranea, MIT 109 (reusable collection for TREC 2002), and Pourpre scoring script for automatically evaluating complex questions.
Neural module networks  Jacob Andreas - code for training and evaluating neural module networks (NMNs). An NMN is a neural network that is assembled dynamically by composing shallow network fragments called modules into a deeper structure. In particular, it contains code to combine NNs for QA.
Open Advancement of Question Answering Systems (OAQA)  
Open Ephyra   - The old version is on the SourceForge
Paralex   - paraphrase-driven learning for Open Question Answering.
ProPPR   - graph-algorithm inferences over local groundings of first-order logic programs
QANTA quiz bowl system  
Question Answering Toolkit  
question-classification   - Question classification into the following 50 classes.
QuestionAnsweringOverFB   - Code for Kun Xu, Siva Reddy, Yansong Feng, Songfang Huang and Dongyan Zhao. Question Answering on Freebase via Relation Extraction and Textual Evidence. In Proceedings of ACL-2016.