Git Product home page Git Product logo

drqa_with_attention's Introduction

DrQA with Multihead Attention

Mô hình dựa trên paper Reading Wikipedia to Answer Open-Domain Questions - Danqi Chen, Adam Fisch, Jason Weston, Antoine Bordes Dataset sử dụng là bộ dataset của cuộc thì Zalo AI 2019 - Vietnamese Wiki Question Answering

So sánh

Màu xanh lam : Model với multihead attn question-context + multihead attn question-question trên bilstm
Màu xanh lá : Model với multihead attn question-context
Màu hồng : Base model
TrainLoss F1 ValLoss

Multiheed attention được implement dựa theo paper Attention Is All You Need - Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin

attn

Setup

Yêu cầu:

  • docker

Setup env:

  • Build docker image: docker-compose build gpu
  • Create docker container: docker-compose build gpu và truy cập jupyter notebook server với address có trong terminal

Training:

  • Run notebook DrQA.ipynb với các config (dataset đã được chuẩn bị trước, xem kĩ hơn tại dataset/qaset/)

Logger:

  • Run notebook TensorboardLogger, cần đặt tên cho experiemnt khi training để dễ phân biệt

drqa_with_attention's People

Contributors

nnhieu avatar

Watchers

James Cloos avatar  avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.