Getting Started with Applied AI and NLP
Last Updated on October 17, 2022 by Editorial Team
Author(s): Daniel Tannor
Originally published on Towards AI the World’s Leading AI and Technology News and Media Company. If you are building an AI-related product or service, we invite you to consider becoming an AI sponsor. At Towards AI, we help scale AI and technology startups. Let us help you unleash your technology to the masses.
Here are 4 Applied AI Project Ideas that You Can Code Right Now
No need for complex self-made Machine Learning Projects — it’s time to use APIs instead. All you need is the coding basics.
Some Background on Natural Language Processing and Applied AI
Applied AI is the branch of artificial intelligence that brings it out of the lab and into the real world, enabling computers and computer-controlled robots to execute real tasks. — cognizant.com
Just like the above quote states — we’re going to use Applied AI so that we can execute real, everyday tasks. We’re also going to leverage Natural Language Processing — getting the machine to process and understand language so that our apps can:
- Figure out which movie scenes are happy so that we can create happy movie scene compilations
- Summarize complete Zoom meetings into short summaries.
The projects are divided up into two categories: Emotion Based and Summarization Based, which I’ll explain in the next paragraph.
The summarization-based projects are meant to be huge time savers and productivity tools — helping people be more effective in reviewing meetings and conversations.
The other projects are meant for entertainment and also improving one’s social skills — whether it’s interviewing, dating, or meeting new people in social settings.
Emotion-based projects are projects that are based on detecting emotions.
When our app manages to detect that an actress in a movie scene was happy, based on the words she said, that makes our project emotion-based.
The emotion-based projects:
Generate Happy Movie Scene Compilations
Do you know those Youtube movie compilations where you get a bunch of scenes that are aligned around an idea?
Here’s an example of a compilation of The Most Beautiful Shots in Movie History
We can use NLP in order to get the happy scenes out of movies and create our own movie compilation- Jim Carrey’s smile comes to mind:
What we’d do is have the NLP engine go over movie scripts and return the time stamps of scenes with the happiness emotion. We’d then attach those scenes together to generate one long clip we can share on YouTube or social media.
You can do this using One AI or other free-to-use NLP APIs you insert in your code. I’ll follow up on this in another blog.
Social Skills Trainer
Often times people don’t know how a conversation went. What if we could build an app to provide feedback and improve people’s social skills?
Below is what the app might look like —
Adam is asking Sarah out, and the conversation starts out pretty awkward. However, you can see that Adam’s last remark gets him points and creates a positive interaction with Sarah.
Adam can now understand which sentences gave him points and which sentences lost him points, and he can improve his interactions with people over time.
See how to build this here.
The summarization-based projects are projects that are based on the NLP engine summarizing large amounts of text in order to provide accurate summaries of content.
This content can also originate in video or audio, we would then transcribe that content so that the AI runs on the text output.
The Summarization projects:
Auto-Summarize Zoom Meetings
Create your own app to auto-summarize Zoom meetings. You can do this per meeting or even build an app to solve this problem at scale.
Aren’t we all tired of long boring meetings? Think of how much time you’d save for yourself and your colleagues if you could provide automatic, accurate summarizations of meetings on a weekly basis.
Some use cases include:
- Summarize your own individual meetings
- Summarize company meetings on a weekly basis for everyone
- Create a web app for people to summarize their meetings
See how to build an app like this here.
Auto-Summarize Slack Conversations
Slack can quickly become one giant mess of information — meeting notes, product requirements, or conversations with the boss.
Can’t find that last feature requirement from last week? What about the notes from your meeting with your 1:1 with your boss?
What if we could build an app to summarize the important points from the past week? These points would include important conversation summaries and action items.
We’ve seen a bunch of different NLP projects you can build today. Some of these ideas, or similar ones, could definitely be the basis of a startup — as they solve real-world pain points that we all experience in our day to day.
We’ve learned about applied AI and NLP to build apps that can help us with day-to-day tasks.
In order to get started, all you need to do is make a few NLP API calls within your code, and you’re good to go.
Please feel free to reach out and share project ideas you have in mind or what you’ve started to build.
Join thousands of data leaders on the AI newsletter. It’s free, we don’t spam, and we never share your email address. Keep up to date with the latest work in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
Published via Towards AI