Problem Statements
Programming Language Classification
Classifying 15 programming languages into different classes
Lingua Franca Translation
Translate Crowd Talk (our new language) to English using Machine Translation
Embedding Game
A puzzle that explores the inner workings of NLP Pre-Processing
👋 Introduction
Language has been an integral part of Human Evolution. Allowing us to share our ideas, thoughts, and feelings with each other, language has enabled us to build societies. If you are reading this right now, it means you have mastered a complex system of words, structure, and grammar to effectively communicate with others. But what about the field that has been enabling our machines to do the same? 🤖
Since the 1950s, Machine Learning has tried to enable machines with some of the cognitive senses that we have mastered. Of its several domains, Natural Language Processing witnesses great growth every year. 🗣️
With the ever-increasing data accessibility and the computational resources available to work with said data, NLP provides an amazing opportunity for an emerging Machine Learning Engineer to make major contributions to the field. 🖥️
AI Blitz⚡comes back with brand new NLP Puzzles
Wanna make your first contribution to this field and take a step into the fast world of Auto-encoders and Transformers? Backed by easy-to-understand Starter Kits and active support from AIcrowd Community, make your first submission in 15-minutes! Following the AI Blitz⚡Tradition, you can win from a cash prize pool of $400 USD!💵
Ready to open your IDEs and write “Hello World NLP”?👋
Let us first look at the puzzles AI Blitz presents you with:
- Programming Language Classification: Classifying a corpus of various programming lines into 15 Programming Languages. ⌨️
- Speaker Identification: Perform clustering on a corpus of transcripts taken from Youtube videos by capturing voiceprints of the given data samples.🎙️
- Language Translation: Perform Language translation from English to Crowd Talk, AIcrowd’s very own made-up language.😉
- Embedding Game: Map an embedding to its root word using NLP techniques.🗺️
- Feature Engineering #2: Perform feature engineering on the data to get the best out of it. ⚙
📅 TIMELINE
- Start Time: 23rd December 2021 | 12:00 PM UTC
- End Time: 13th January 2022 | 12:00 PM UTC
- Duration: 21 days/3 weeks
💻 INSTRUCTIONS
- Each problem has an associated weight. This weight denotes the problem’s contribution to your final score.
- The final leaderboard is calculated by the weighted mean of your rank across all the problems in the contest. If a problem is not attempted by the participant, his/her rank in that problem is denoted by the total number of participants in the whole challenge.
- To help you "Get Started" we have a starter kit available for each of these problems. We hope they are helpful; if you find any bugs, typos, or improvements, please send us a pull request.
- In case you have any queries, please reach out to us via the Discussion Forums.
🏆 PRIZES
- Leaderboard 1st Place: $100
- Leaderboard 2nd Place: $100
- Community Contribution: 2 x $100
🧾 ELIGIBILITY
AI BlitzXII⚡ is open to everyone who is interested in diving into the world of Data sciences - students, professionals, or researchers. With problems of varying difficulty, we try to ensure that there is something for everyone. For eligibility on prizes please read the rules of the challenge.
Problem Setter: Aditya Jha, Shubhamai, Dipam Chakraborty, Sharada Mohanty, Ayush Shivani
Team: Aditya Jha, Shubhamai, Aryan Kargwal, Akanksha Tyagi, Gauransh Kumar, Sneha Nanavati, Ayush Shivani, Sharada Mohanty, Rabiul Islam
Interested in helping us out or want to put your own puzzle in the next iteration of this competition? Please send an email to ashivani@aicrowd.com.
Interested in sponsoring AI Blitz in the next iteration of this competition? Please send an email to mohanty@aicrowd.com.
📱 CONTACT
If you have any questions, consider posting on the Blitz 12 Community Discussion board, or join the party on our Discord!
Participants
Leaderboard
01 | youssef_nader3 | 470.000 |
02 | nicholas_liu | 520.000 |
03 | mkeywood | 735.000 |
04 | victorkras2008 | 790.000 |
05 |
|
885.000 |