Media Summary: It's easy to get distracted when you go down the rabbit hole of In this third video of the series we will In the previous video, we've started measuring bias in word embeddings. In this video, we will attempt to remove some of this bias ...
Rasa Algorithm Whiteboard Meaningful Benchmarks - Detailed Analysis & Overview
It's easy to get distracted when you go down the rabbit hole of In this third video of the series we will In the previous video, we've started measuring bias in word embeddings. In this video, we will attempt to remove some of this bias ... In the previous videos, we've started measuring bias in word embedding and tried to counteract the bias with a linear algebra ... In this video, we'll highlight a qualitative argument of why you may not need to worry about pre-trained embeddings too much. When you iterate on your data, you also want to iterate on your model. It'd be a shame to have to retrain from scratch every single ...
We're starting a new playlist! Introducing the In this video, we will discuss some technical details that are in the UnexpecTEDIntentPolicy. The UnexpecTEDIntentPolicy really is ... In the previous video on bias, we showed that you should be careful with debiasing techniques. In this video, we zoom in on why ... The way the response selector is implemented in In the age of deep learning and transformers, rule-based systems can still be a great idea. In this video, we hope to demonstrate ... This is the second video on attention mechanisms. In the previous video we introduced self attention and in this video we're going ...
When you're uncertain about a prediction it's probably best not to immediately automate it. In this video, we'll discuss a fallback ... Instead of debugging a model, it might be *much* more effective to consider debugging your data. In this video, we'll discuss ... When people refer to a Machine Learning backend, they typically call it a "pipeline". A pipeline is a nice mental concept, and ... In the previous video we've discussed the "how" the model works. In this video we hope to explain "why" the architecture looks this ... In this video, we will explore pre-trained spaCy models and use them to detect names. These pre-trained models are great, but ... What if we design a policy mechanism that doesn't predict the next action to take, but instead predicts when something ...
Sometimes you can change the intent labels to get a more accurate model. In this video, we will explore how to do this with a ...
