GithubHelp home page GithubHelp logo

jasonforjoy / u2u-imn Goto Github PK

View Code? Open in Web Editor NEW
6.0 3.0 1.0 21 KB

TASLP: Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots

Python 95.70% Shell 4.30%
multi-turn-dialogue response-selection chatbot

u2u-imn's Introduction

Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots

This repository contains the source code and datasets for the IEEE/ACM Transactions on Audio, Speech and Language Processing paper Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots by Gu et al.

Dependencies

Python 2.7
Tensorflow 1.4.0

Datasets

Your can download the processed datasets used in our paper here and unzip it to the folder of data.
Ubuntu_V2

Train a new model

cd scripts
bash ubuntu_train.sh

The training process is recorded in log_train_UbuntuV2.txt file.

Test a trained model

bash ubuntu_test.sh

The testing process is recorded in log_test_UbuntuV2.txt file. And your can get a ubuntu_test_out.txt file which records scores for each context-response pair. Run the following command your can compute the metric of Recall.

python compute_recall.py

Cite

If you use the code and datasets, please cite the following paper: "Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots" Jia-Chen Gu, Zhen-Hua Ling, Quan Liu. TASLP

@ARTICLE{8910440,
         author={J. {Gu} and Z. {Ling} and Q. {Liu}},
         journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
         title={Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots},
         year={2020},
         volume={28},
         number={},
         pages={369-379},
         keywords={Context modeling;Encoding;Buildings;Neural networks;Training;Dialogue;response selection;interactive matching network;utterance-to-utterance},
         doi={10.1109/TASLP.2019.2955290},
         ISSN={2329-9304},
         month={},}
}

u2u-imn's People

Contributors

jasonforjoy avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

Forkers

luweishuang

u2u-imn's Issues

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.