BLEURT - Learning Robust Metrics for Text Generation
Offered By: Yannic Kilcher via YouTube
Course Description
Overview
Explore a comprehensive video explanation of the BLEURT paper, which proposes a learned evaluation metric for text generation models. Dive into the challenges of evaluating machine translation systems and learn how BLEURT addresses these issues through a novel pre-training scheme using synthetic data. Discover the key components of the approach, including fine-tuning BERT, generating synthetic data, and priming via auxiliary tasks. Examine the experimental results, distribution shifts, and potential concerns associated with this innovative metric. Gain insights into the state-of-the-art performance of BLEURT on recent WMT Metrics shared tasks and the WebNLG Competition dataset.
Syllabus
- Intro & High-Level Overview
- The Problem with Evaluating Machine Translation
- Task Evaluation as a Learning Problem
- Naive Fine-Tuning BERT
- Pre-Training on Synthetic Data
- Generating the Synthetic Data
- Priming via Auxiliary Tasks
- Experiments & Distribution Shifts
- Concerns & Conclusion
Taught by
Yannic Kilcher
Related Courses
Sentiment Analysis with Deep Learning using BERTCoursera Project Network via Coursera Natural Language Processing with Attention Models
DeepLearning.AI via Coursera Fine Tune BERT for Text Classification with TensorFlow
Coursera Project Network via Coursera Deploy a BERT question answering bot on Django
Coursera Project Network via Coursera Generating discrete sequences: language and music
Ural Federal University via edX