Code Monkey home page Code Monkey logo

entheos-dataset's Introduction

Logo

Entheos-Dataset

Source code for "Entheos: A Multimodal Dataset for Studying Enthusiasm" (Carla Viegas and Malihe Alikhani - ACL 2021).

Dependencies

  • Pytorch (follow instructions on official website
  • Skorch
    pip install -U skorch
  • Python 3.6 or higher

Other dependencies can be found in the Pipfile.

Usage

In the bash script run.sh you can find commands to start training the best unimodal and best multimodal models. If you want to train all of them simply run:

bash run.sh

If you want to train a model with different modalities, create a new config file similar to the existing ones, changing the "feature" and "modalities" entry to what you desire. In the CSVFeatures folder are all features extracted from the different modalities. This allows you to easily choose the modalities you want to use by adding the path to the CSV files in the config files.

Reference

Please cite the paper below if you use this code in your research:

@inproceedings{viegas2021entheos,
	Address = {Online},
	Author = {Viegas, Carla and Alikhani, Malihe},
	Booktitle = {Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021},
	Date-Added = {2021-08-04 14:21:26 -0400},
	Date-Modified = {2021-08-04 14:22:05 -0400},
	Doi = {10.18653/v1/2021.findings-acl.180},
	Month = aug,
	Pages = {2047--2060},
	Publisher = {Association for Computational Linguistics},
	Title = {Entheos: {A} Multimodal Dataset for Studying Enthusiasm},
	Url = {https://aclanthology.org/2021.findings-acl.180},
	Year = {2021},
	Bdsk-Url-1 = {https://aclanthology.org/2021.findings-acl.180},
	Bdsk-Url-2 = {https://doi.org/10.18653/v1/2021.findings-acl.180}}

Acknowledgements

This work was supported by TalkMeUp Inc.

entheos-dataset's People

Contributors

clviegas avatar

Stargazers

 avatar  avatar  avatar

Watchers

 avatar

entheos-dataset's Issues

Other auditory features

eGeMAPS-features are available in the CSVFeatures-folder, but other auditory features aren’t. Could the other features mentioned in the paper (IS09, IS10, IS13) be included in the CSVFeatures-folder? Additionally, a text file containing the timestamps, which were used to split the data, would allow me to split the TED-talks according to train.csv and test.csv.

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.