vinhkhuc / Memn2n Babi Python
Licence: other
End-To-End Memory Networks for bAbI question-answering tasks
Stars: ✭ 570
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Memn2n Babi Python
Bert Squad
SQuAD Question Answering Using BERT, PyTorch
Stars: ✭ 256 (-55.09%)
Mutual labels: question-answering
Giveme5w1h
Extraction of the journalistic five W and one H questions (5W1H) from news articles: who did what, when, where, why, and how?
Stars: ✭ 316 (-44.56%)
Mutual labels: question-answering
Cdqa
⛔ [NOT MAINTAINED] An End-To-End Closed Domain Question Answering System.
Stars: ✭ 500 (-12.28%)
Mutual labels: question-answering
Anspress
AnsPress is the most complete question and answer system for WordPress. AnsPress is made with developers in mind, highly customizable. AnsPress provide an easy to use override system for theme
Stars: ✭ 264 (-53.68%)
Mutual labels: question-answering
Spm toolkit
Neural network toolkit for sentence pair modeling.
Stars: ✭ 301 (-47.19%)
Mutual labels: question-answering
Cogqa
Source code and dataset for ACL 2019 paper "Cognitive Graph for Multi-Hop Reading Comprehension at Scale"
Stars: ✭ 399 (-30%)
Mutual labels: question-answering
AskNowNQS
A question answering system for RDF knowledge graphs.
Stars: ✭ 32 (-94.39%)
Mutual labels: question-answering
Rust Bert
Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)
Stars: ✭ 510 (-10.53%)
Mutual labels: question-answering
Informers
State-of-the-art natural language processing for Ruby
Stars: ✭ 306 (-46.32%)
Mutual labels: question-answering
Mac Network
Implementation for the paper "Compositional Attention Networks for Machine Reasoning" (Hudson and Manning, ICLR 2018)
Stars: ✭ 444 (-22.11%)
Mutual labels: question-answering
Nlu sim
all kinds of baseline models for sentence similarity 句子对语义相似度模型
Stars: ✭ 286 (-49.82%)
Mutual labels: question-answering
Node Question Answering
Fast and production-ready question answering in Node.js
Stars: ✭ 294 (-48.42%)
Mutual labels: question-answering
Gnn4nlp Papers
A list of recent papers about Graph Neural Network methods applied in NLP areas.
Stars: ✭ 405 (-28.95%)
Mutual labels: question-answering
Qa Survey
北航大数据高精尖中心研究张日崇团队对问答系统的调研。包括知识图谱问答系统(KBQA)和文本问答系统(TextQA),每类系统分别对学术界和工业界进行调研。
Stars: ✭ 502 (-11.93%)
Mutual labels: question-answering
Adam qas
ADAM - A Question Answering System. Inspired from IBM Watson
Stars: ✭ 330 (-42.11%)
Mutual labels: question-answering
Paper Reading
Paper reading list in natural language processing, including dialogue systems and text generation related topics.
Stars: ✭ 508 (-10.88%)
Mutual labels: question-answering
Deep qa
A deep NLP library, based on Keras / tf, focused on question answering (but useful for other NLP too)
Stars: ✭ 409 (-28.25%)
Mutual labels: question-answering
End-To-End Memory Networks for Question Answering
This is an implementation of MemN2N model in Python for the bAbI question-answering tasks as shown in the Section 4 of the paper "End-To-End Memory Networks". It is based on Facebook's Matlab code.
Requirements
- Python 2.7
- Numpy, Flask (only for web-based demo) can be installed via pip:
$ sudo pip install -r requirements.txt
-
bAbI dataset should be downloaded to
data/tasks_1-20_v1-2
:
$ wget -qO- http://www.thespermwhale.com/jaseweston/babi/tasks_1-20_v1-2.tar.gz | tar xvz -C data
Usage
- To run on a single task, use
babi_runner.py
with-t
followed by task's id. For example,
python babi_runner.py -t 1
The output will look like:
Using data from data/tasks_1-20_v1-2/en
Train and test for task 1 ...
1 | train error: 0.876116 | val error: 0.75
|=================================== | 71% 0.5s
- To run on 20 tasks:
python babi_runner.py -a
- To train using all training data from 20 tasks, use the joint mode:
python babi_runner.py -j
Question Answering Demo
- In order to run the Web-based demo using the pretrained model
memn2n_model.pklz
intrained_model/
, run:
python -m demo.qa
- Alternatively, you can try the console-based demo:
python -m demo.qa -console
- The pretrained model
memn2n_model.pklz
can be created by running:
python -m demo.qa -train
- To show all options, run
python -m demo.qa -h
Benchmarks
See the results here.
Author
Vinh Khuc
Future Plans
- Port to TensorFlow/Keras
- Support Python 3
References
- Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, Rob Fergus, "End-To-End Memory Networks", arXiv:1503.08895 [cs.NE].
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].