Giter Site home page Giter Site logo

e-kiss-me / core Goto Github PK

View Code? Open in Web Editor NEW

This project forked from core-labet/core

0.0 0.0 0.0 6.79 MB

CORE is a plug-and-play conversational agent for any recommender system.

Home Page: https://jinjiarui.github.io/core/

License: Apache License 2.0

Python 100.00%

core's Introduction

Conversational Agent for Recommender System (CORE)

Project | Paper | Documentation

CORE is a plug-and-play conversational agent for any recommender system built upon PyTorch. CORE is:

  • Comprehensive: CORE provides a data manager, an offline trainer, and an online checker.
  • Flexible: CORE could be integrated into any recommender system.
  • Efficient: CORE is built upon an online decision tree algorithm instead of heavily learning algorithms.

Brief Introduction

CORE is a new offline-training and online checking paradigm that bridges conversational agent and recommender systems via a unified uncertainty minimization framework. It could benefit any recommendation platform in a plug-and-play style. Here, CORE treats a recommender system as an offline relevance score estimator to produce an estimated relevance score for each item; while a conversational agent is regarded as an online relevance score checker to check these estimated scores in each session. We define uncertainty as the summation of unchecked relevance scores. In this regard, the conversational agent acts to minimize uncertainty by querying either attributes or items. Based on the uncertainty minimization framework, we derive the expected certainty gain of querying each attribute and item and develop a novel online decision tree algorithm to decide what to query at each turn.

Use Cases

The significant advantage of CORE is that CORE can be easily deployed on any existing recommendation platform because CORE acts as a bridge connecting the conversational agent and recommender agent. In other words, in the proposed offline-training and online-checking paradigm, CORE only requires the estimated relevance scores from the recommender agent and the render (including both text extractor and text generator) from the conversational agent.

ToDo (Latest Update at 2023/07/24)

  • Release top-1 Recommendation where action space includes candidate items (e.g., whether she likes a dress), candidate attributes (e.g., what color she likes), and candidate attribute values (e.g., whether she likes a red dress).
  • Release top-N recommendation where action space includes
  • Release large language models based render to allow the conversational agent to communicate like humans.
  • Release pre-processed datasets and more datasets with textual features.
  • Release detailed document tutorial and readme guidance.

Citing CORE

@software{CORE,
  author = {Jiarui Jin, Xianyu Chen, Fanghua Ye, Mengyue Yang, Yue Feng, Weinan Zhang, Yong Yu, and Jun Wang},
  title = {CORE: A Plug-and-Play Conversational Agent for Recommender System},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  version = {0.0},
  howpublished = {\url{https://github.com/CORE-Labet/CORE}},
}

The Team

Core developers of the CORE system are Jiarui Jin and Xianyu Chen.

License

CORE is released under the Apache License, Version 2.0.

core's People

Contributors

jinjiarui avatar

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.