Giter VIP home page Giter VIP logo

recommender-system's Introduction

Relationship-Scenario based Trailer Recommendation(RSTR)

PPT
RSTR Demo
RSTR DataBase
RSTR API Test
Paper
Committee member comment

Overview Flow

  • Pretrained Model(I used 3 kind of embeddings method)
  1. BERT(trained: wiki(WordPiece), fine tunning: single article or single storyline)
  2. Word2Vec-SG(Train Data: dcard mood article(Entity), yahoo and pixnet storyline(Entity))
  3. Word2Vec-SG(Train Data: dcard mood article(Word), yahoo and pixnet storyline(Word))
  • Feature Generation
  1. E2V-BERT 透過產生的斷詞進行辭典過濾並得到各個 entity 在進行 relationship feature 和 scenaio feature 的產生
  2. E2V-W2V-SG 透過產生的斷詞進行辭典過濾並得到各個 entity 在進行 relationship feature 和 scenario feature 的產生
  3. W2V-W2V-SG(relationship model baseline) 單純的斷詞未經過辭典產生 word 並做詞向量相加
  • Relationship Classifer
    relationship classifier 訓練(relationship_algorithm_analysis) > 供給 server 存取(main)
  • Scenario Classifier
    scenario classifier 訓練(scenario_algorithm_analysis) > 供給 server 存取(main)

Main

RecommenderSystem

目的:NER 運用(Insert Article, Movie Parser and Article, Movie NER), Server 架設
執行:activator "start 8309"(註:java project)

main

目的:存取模型結果, Server 架設
執行:python3 server.py(註:python project)

token

執行:python3 service_Server.py(註:python project)

Module

main_embedding

目的:訓練 Entity2Vec-BERT, Entity2Vec-W2V-SG, Word2Vec-W2V-SG(baseline) 並將 relationship feature and scenario feature 存入

relationship_algorithm_analysis

目的:訓練 relationship 模型(CNN)

scenario_algorithm_analysis

目的:訓練 scenario 模型(KNN, NB, SVM, RFC)

rstr_evaluation

目的:給予評分項目,產生評估結果

knowledge base

目的:產生 relationship lexicon(person), emotion lexicon(emotion), time lexicon(time), location lexicon(location)and event 辭典

article(Dcard Mood)

目的:爬蟲, 存取資料庫, CKIP Parser

movie(Pixnet and Yahoo)

目的:爬蟲, 存取資料庫, CKIP Parser

test

目的:測試資料用

View

rstr_view

目的:推薦系統介面

rstr_view_evaluation

目的:評估系統介面

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.