Code Monkey home page Code Monkey logo

moca's Introduction

Reproducing Momentum Calibration for Text Generation Paper

Part of onboarding task for Forward Data Lab Summer 2023, I reproduced the current state-of-the-art abstractive text summerication method: Momentum Calibration for Text Generation (MoCA) using huggingface and pytorch. See Final Report for this task.

Results:

Rouge 1 Rouge 2 Rouge L
Vanilla Finetuned Baseline in the MoCa Paper 44.22 21.22 41.01
MoCa Paper 48.88 24.94 45.76
Vanilla Finetuned Baseline in the BART paper 40.95 20.81 40.04
My Implementation 46.04 22.61 42.93

Running the code

  • Set/Change the environment variable for selecting GPUs to use.
  • Run python MoCa.py to apply MoCA on model.
  • Run evaluation.ipynb to evaluate model on ROUGE score.

moca's People

Contributors

markintoshz avatar

Watchers

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.