AugSBERT: Domain Transfer for Sentence Transformers
Offered By: James Briggs via YouTube
Course Description
Overview
Learn how to effectively transfer information from out-of-domain datasets to your target domain using the AugSBERT training strategy in this comprehensive video tutorial. Discover techniques for quickly assessing source dataset alignment with your target domain, and explore the step-by-step process of implementing the AugSBERT domain-transfer training strategy. Gain insights into training source cross-encoders, labeling target data, and evaluating bi-encoder performance to optimize your language models for semantic search applications. Perfect for NLP practitioners and researchers looking to enhance their model's performance through domain transfer techniques.
Syllabus
Why Use Domain Transfer
Strategy Outline
Train Source Cross-Encoder
Cross-Encoder Outcome
Labeling Target Data
Training Bi-encoder
Evaluator Bi-encoder Performance
Final Points
Taught by
James Briggs
Related Courses
Microsoft Bot Framework and Conversation as a PlatformMicrosoft via edX Unlocking the Power of OpenAI for Startups - Microsoft for Startups
Microsoft via YouTube Improving Customer Experiences with Speech to Text and Text to Speech
Microsoft via YouTube Stanford Seminar - Deep Learning in Speech Recognition
Stanford University via YouTube Select Topics in Python: Natural Language Processing
Codio via Coursera