Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Freestyle Challenge: Swiss German - Basel Deutsch Challenge #4

Open
11 tasks
esthicodes opened this issue Oct 15, 2022 · 0 comments
Open
11 tasks

Freestyle Challenge: Swiss German - Basel Deutsch Challenge #4

esthicodes opened this issue Oct 15, 2022 · 0 comments
Assignees

Comments

@esthicodes
Copy link

esthicodes commented Oct 15, 2022

Challenge Name

Swiss German Speech-to-Text NLP Bot

Team Members

Please list any teams members that already showed interest to work on this challenge. You can also keep this section empty.

  • Member 1 Esthi Yu
  • Member 2 Raphaella Baur
  • Member 3 Caleb Jung*

Team Open To Others?

Please specify if your team is open for other BaselHack participants to join. BaselHack recommends team sizes of about 5 persons. A team needs to have at least 2 members and at most 10 members.

We explore how we can automatically process natural language to analyse and create media content and how recent advances in deep learning can affect how we work, consume, and interact with natural language in the future.

[Yes]

Challenge Pitch

This challenge is to explain Lineare Algebra in Swiss German evaluate how Speech-to-Text performs in real-world scenarios. We are developing an Artificial Intelligence like Siri which offers a faster, easier way to get things done on Apple devices with OpenAPI. Millions of people now use Siri to send a message, play their favorite song or even take a selfie. We are using NLP and Backpropagation that demonstrates active listening, integrity and acute attention to detail.

Datasets

If applicable, please state what datasets are publicly avaialable or what private datasets you can bring to the hackathon.``

We have some datasets from different languages which are memes and Swiss German Languages. Generate a high-quality data set. There is a lack of speech datasets for Swiss-German texts. This is why the first part of this project will focus on generating a high-quality data set of 26 different Swiss German dialects and comments to detect stance and emotions. For this we will use an appropriate crowdsourcing setup informed by previous work on crowdsourcing similar tasks.

Datasets:

Datasets

Goals:

  • Build an AI that is fluent in Swiss German language with excellent comprehension, grammar and proofreading skills.

  • Excellent active listening skills with the ability to understand verbal nuances in the Swiss German dialect, including the variations across different provinces and territories.

  • Demonstrates attention to detail and critical thinking skills in evaluation of Siri’s language usage and dialect.

  • Ability to independently navigate systems and tools.

  • Demonstrates integrity and focuses on customer privacy

  • Content review or a similar environment, prior testing experience preferred

  • Demonstrates flexibility and adaptability to changing work-flows and responsibilities

  • Experience as an end user of Siri, similar Intelligent Personal Assistants, or other AI

  • Successfully meets or exceeds targets, working within tight deadlines

  • Ability to identify process solutions that increase efficiencies

  • Ability to maintain focus and aim for high results through large volumes of datasets.

P.S.

Please have a look at the following example or resources for further feedback.

SwissGerman_Dictionary

algorithms

@rordi rordi changed the title 26 Swiss German - Basel Deutsch Challenge Freestyle Challenge: Swiss German - Basel Deutsch Challenge Oct 17, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants