资源算法MemN2N-babi-python

MemN2N-babi-python

2020-01-11 | |  36 |   0 |   0

End-To-End Memory Networks for Question Answering

This is an implementation of MemN2N model in Python for the bAbI question-answering tasksas shown in the Section 4 of the paper "End-To-End Memory Networks". It is based on Facebook's Matlab code.

687474703a2f2f692e696d6775722e636f6d2f6d4b745a376b422e676966.gif

Requirements

  • Python 2.7

  • Numpy, Flask (only for web-based demo) can be installed via pip:

$ sudo pip install -r requirements.txt
$ 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 in trained_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


上一篇:MemN2N-tensorflow

下一篇:MemN2N-UDC

用户评价
全部评价

热门资源

  • TensorFlow-Course

    This repository aims to provide simple and read...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • mxnet_VanillaCNN

    This is a mxnet implementation of the Vanilla C...

  • DuReader_QANet_BiDAF

    Machine Reading Comprehension on DuReader Usin...

  • Klukshu-Sockeye-...

    KLUKSHU SOCKEYE PROJECTS 2016 This repositor...