CohereAIHack Challenge
▷Build a solution that incorporates Cohere's Multilingual Embeddings Model◁
Innovation is a critical component of progress and growth, and fostering creativity and collaboration is key to driving innovation. However, in many context, communication barriers, cultural differences, and other factors can impede innovation and limit its potential impact. To foster innovation in Africa and beyond, we challenge participants to develop a solution that leverages Cohere's multilingual embedding to enhance communication, collaboration, and creativity among individuals and organizations.
The official hackathon dates are 28th April - 13th of May, 2023 (online + in-person hacking possible on the 6th of May for certain locations). See the rules page for more information.
Once a team is formed, register your team's name in the registration form. The deadline is Friday 5th of May 2023, 23:59 WAT.
Your Solution
- Should leverage Cohere's multilingual embedding to develop a tool or application that empowers innovation in a specific domain or context.
- Should be innovative, user-friendly, and have the potential to impact a wide range of individuals and organizations.
Get started
Cohere's Multilingual Model maps text to a semantic vector space, positioning text with a similar meaning in close proximity. This process unlocks a range of valuable use cases for multilingual settings. For example, one can map a query to this vector space during a search to locate relevant documents nearby. This often yields search results that are several times better than keyword search.
Cohere's multilingual embedding supports over 100 languages across the world. These are some of machine learning tasks that are possible with this model
- Semantic Search: you can build an app that enables users to search using conversational language
- Topic Modeling: you can cluster similar topics and discover thematic trends across a body of text sources
- Recommendations: you can build a recommendation engine and engage your users with more relevant content
- Multilingual embedding: you can run a topic modelling, semantic search, and recommendations across 100+ languages with just one model
Requirements
What to Build
✨ Let your creativity shine.✨ You can use cohere's embed model to create a solution such as
- Creating a platform that connects innovators across different languages and cultures
- Developing a machine learning model that can identify and address barriers to innovation in a specific industry or sector
- Designing a natural language processing (NLP) system that can help users generate and refine innovative ideas more efficiently.
- And so much more
What to Submit
- Project name
- Github repository and demo link
- 3-5 minutes video walkthrough of your solution
- Presentation slides
Prizes
$2,500 in prizes
First Place
+ 3000 Cohere API Credits and will get to meet with one of Cohere’s founders and work with Cohere team to build a demo package for social media feature.Prizes are spilt among team members
Second Place
+2000 Cohere API Credits.Prizes are spilt among team members
Third Place
+1000 Cohere API Credits. Prizes are spilt among team members
Fourth Place
+500 Cohere API Credits. Prizes are spilt among team members
Honourable mentions
(2)
+500 Cohere API Credits. Prizes are spilt among team members
Devpost Achievements
Submitting to this hackathon could earn you:
Judges

Tejumade Afonja
Co-founder / AI Saturdays Lagos

Roy Lim
Marketing Events Manager / Cohere

Luiza Pozzobon
Research Scholar / Cohere For AI

Jesujoba Alabi
Ph.D. student / Saarland University

Luísa Moura
Member of Technical Staff / Cohere

Marina Machado
Member of Technical Staff / Cohere
Judging Criteria
-
Idea Quality
How creative, original or innovative is the idea? -
Implementation of Idea
How well was the idea implemented technologically? Did the solution use Cohere's multilingual embedding? Did the solution incomporates other Cohere's technology (This is not mandatory but is encouraged). -
Potential Impact
Does the solution have a real-world (social) impact and does it provide some sort of value to users? -
Pitch
Did the pitch communicate why the team settled on the specific solution? Were they able to articulate the value to users? -
Popular Vote
Once you have submitted your project, you will be able to look at other people's project and vote for the project that you like. We will take this into consideration for the final evaluation.
Questions? Email the hackathon manager
Tell your friends
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.