The explainable AI whiteboard technical series explores and explains some of the key tools within our data science toolbox that powers the Juniper AI-Native Networking Platform. In this video we cover natural language processing.
Juniper’s Natural Language Processing (NLP) in AIOps enables machines to understand human language, enhancing tools like Marvis, the virtual network assistant. NLP interprets user questions to provide actionable insights, starting with text cleanup and tokenization, splitting text into smaller units. These are featurized, converting words into vectors that represent their meaning, with similar words mapped closer together in multi-dimensional space.
Pre-trained embedding models use large datasets like Wikipedia to encode complex word meanings. These embeddings are fed into a machine learning model, predicting the meaning of new words based on their similarity to known vectors.
Juniper builds on this with a training dataset of real customer questions, annotated with intents (e.g., troubleshoot) and entities (e.g., device name), enabling Marvis to accurately predict actions. NLP allows rapid problem resolution and streamlines operations, making Marvis a valuable virtual team member in AI-Native networking solutions.
Chapters:
0:00: Introduction
1:12 Featurization
1:44 Embedding models
What is explainable AI, or XAI?
https://www.juniper.net/us/en/research-topics/what-is-explainable-ai-xai.html
Explainable AI
https://www.juniper.net/us/en/dm/explainable-ai.html
Juniper’s Natural Language Processing (NLP) in AIOps enables machines to understand human language, enhancing tools like Marvis, the virtual network assistant. NLP interprets user questions to provide actionable insights, starting with text cleanup and tokenization, splitting text into smaller units. These are featurized, converting words into vectors that represent their meaning, with similar words mapped closer together in multi-dimensional space.
Pre-trained embedding models use large datasets like Wikipedia to encode complex word meanings. These embeddings are fed into a machine learning model, predicting the meaning of new words based on their similarity to known vectors.
Juniper builds on this with a training dataset of real customer questions, annotated with intents (e.g., troubleshoot) and entities (e.g., device name), enabling Marvis to accurately predict actions. NLP allows rapid problem resolution and streamlines operations, making Marvis a valuable virtual team member in AI-Native networking solutions.
Chapters:
0:00: Introduction
1:12 Featurization
1:44 Embedding models
What is explainable AI, or XAI?
https://www.juniper.net/us/en/research-topics/what-is-explainable-ai-xai.html
Explainable AI
https://www.juniper.net/us/en/dm/explainable-ai.html
- Category
- Juniper Networks
- Tags
- AI, AIOps, ML
Be the first to comment


