Key Concepts
Azimuth leverages different analyses and concepts to enhance the process of dataset analysis and error analysis.
The notion of smart tags is the most important concept, as it unifies most of the other analyses.
Smart Tags
Smart tags are assigned to utterances by Azimuth when the app is launched. They can be seen as meta-data on the utterance and/or its prediction. The goal is to guide the error analysis process, identifying interesting data samples which may require further action and investigation. Different families of smart tags exist, based on the different types of analyses that Azimuth provides.
Smart tag examples
Examples of smart tag families:
- partial syntax: identifies utterances with a partial syntax, e.g. missing a verb.
- behavioral testing: identifies utterances which failed at least one behavioral test.
Examples of individual smart tags:
long_sentencesidentifies utterances with more than X tokens.failed_punctuationidentifies utterances that failed at least one punctuation test.
The full list of smart tags is available in Smart Tags.
Proposed Actions
While smart tags are computed automatically and cannot be changed, proposed actions are annotations that can be added by the user to identify a proposed action that should be done on a specific data sample.
Proposed action examples
relabelto identify data samples whose labels should be changed.removeto identify data samples that should be removed from the dataset.
A dedicated page on Proposed Actions gives the full list of available actions.
Prediction Outcomes
Another key concept used through the application is the notion of prediction outcomes. It acts as a metric of success for a given prediction. More details are available in Prediction outcomes.
- Correct & Predicted
- Correct & Rejected
- Incorrect & Rejected
- Incorrect & Predicted
Analyses
In Azimuth, different types of analysis are provided. Each analysis has a dedicated section in the documentation. Almost all of them (except saliency maps) are linked to smart tags.