News headline generator for Match TV
Neural Networks, AI
Client
Match TV is a federal sports TV channel, as well as a website with news, interviews, sports statistics and match broadcasts
Solution
Neural network service for real-time news headline generation
To launch sports channels in Telegram and Twitter, which will be led by artificial intelligence. The project was timed to coincide with the 2020 European Football Championship
Task
Main information
01/
How it works
02/
A neural network analyzes news headlines and creates its own variations
The editor looks through the options and selects the most interesting ones
Headlines with summaries of the news are published on Match TV channels
Sergey Verentsov
Project Developer
Quote
«The neural network was trained on Match TV news headlines and the yellow press. That's why the choices it offered were quite provocative. The best headlines were selected and published manually»
Service features
03/
The neural network was packed into a Telegram chat bot for convenience
The neural network answered questions. The editor could ask them through the bot
The service could finish the headline - the editor just needed to make up the beginning
Sergey Verentsov
Project Developer
Quote
«To train the neural network, we collected all of Match TV's headlines since the site's launch in 2003. As you know, the more data that is used to train a service, the better the results»
Project Developer
Sergey Verentsov
The team and timeline
04/
2 weeks
Development time
May 2020
Stages of development
05/
preparation of the dataset for training the neural network
testing the service together with the client
training on Match TV and other sports media headlines
integration of a neural network into a Telegram chatbot
complete service launch
Technologies
06/
GPT-2
(Generative Pre-trained Transformer 2) is an open-source AI developed by the American company OpenAI
zDialog
EORA's own chatbot builder
Project results
07/
Now we have created a pipeline for generating any text - not only news titles, but also, for example, product names, product descriptions. The only thing we will need is data on which the neural network can learn
Sergey Verentsov
Project Developer
The neural network successfully worked for 1.5 months from June to July 2021
Perfume Consultant for Alice Assistant
Skill Quiz
Interactive fairy tales in Google Assistant
Similar projects
09/