| ADAM - a Question Answering System. Inspired from IBM Watson
|
| Aqqu - More Accurate Question Answering on Freebase
|
| askplatypus |
| 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.
|
