AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
What the Human Brain Can Tell Us About NLP Models with Allyson Ettinger - #483
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
The Models Are Picking Up on Spurious Correlations
In question answering data sets, you have models that will pick up on kind of spurious correlations. And here what you're doing, in some ways, is a subset and that the questions you're answering is about one specific type of sematic relationship. The information that they get masks a specific type of,. i don't know if you would call it noise, or relationship with the word order in particular. So you are kind of taking that out of the equation for the model. Yes, absolutely. I can imagine a version of our test. That's less carefully controlled, that may show very high accuracies. This could lead us to believe that the models are great at semantic roll.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode