Simon / Pixabay

 

Google’s Bard has been playing “catch-up” with ChatGPT this year.

Today, they made some strides toward their goal.

Here’s one big upgrade:

Starting today, you can collaborate with Bard in over 40 languages, including Arabic, Chinese, German, Hindi and Spanish.

This feature will be a big help to English Language Learners!  When they are using it to practice English (see HERE IS A LIST OF GAMES CHATGPT SAYS IT CAN PLAY WITH ELLS TO HELP THEM LEARN ENGLISH) and asking for comprehensible feedback in their home language about their errors,  or when asking for feedback in their home language about their English writing (which is what I had students do in the spring with ChatGPT), they’ll be able to get it.

Here’s the other new feature:

Sometimes hearing something out loud can help you approach your idea in a different way. That’s why, starting today, you can listen to Bard’s responses. This is especially helpful if you want to hear the correct pronunciation of a word or listen to a poem or script. Simply enter a prompt and select the sound icon to hear Bard’s answers. This feature is now live in over 40 languages.

As far as I can tell, though you can give  ChatGPT audio instructions (though only on the iPhone app, not on the web version), there’s not a way for you to hear what it says (though I assume there are some plug-ins you can get that would allow it).

This new Bard ability will be a big help to ELLs who have low literacy in their home language.

Getting feedback on mistakes and errors in a student’s home language is great, but getting it only in writing doesn’t really help those who have low literacy in it.

For example, a student can now give Bard a prompt like this:

I am an English language learner give me three sentences that I can pronounce and you can give me feedback on it. Give me that feedback in Spanish.

They can copy-and-paste that prompt into it, or make some minor modifications so they can say it in Spanish.

Then, they just have to click on the microphone icon in Bard and it will provide the audio.

I was disappointed in how one of their other new features worked:

Use images in your prompts: Images are a big part of how we put our imaginations to work. At I/O we announced we’re bringing the capabilities of Google Lens into Bard. Whether you want more information about an image or just need help coming up with a caption, you can now upload images with prompts and Bard will analyze the photo to help. This feature is now live in English, and we’ll expand to new languages soon.

I had hoped this, too, would help ELLs.  Here’s a prompt I tried:

I am learning English. I will describe this picture. Please tell me what part of my description is correct and which part is incorrect: A man is looking at the camera. He is bald. He is wearing a tie and a sport coat. A whiteboard is in front of him.

I received this response:

Sorry, I can’t help with images of people yet.

I then tried doing the same thing with an image that didn’t have any people in it, but received the same response.  Sigh.

But, I’m assuming they’ll get that working better in the near future.

 

I’m adding this info to:

THE BEST POSTS ABOUT USING ARTIFICIAL INTELLIGENCE WITH ELLS

My Best Posts On Artificial Intelligence In The Classroom

THE BEST SITES FOR ONLINE PRONUNCIATION FEEDBACK – DO YOU KNOW OTHERS?