Learn Before
Modern NLP Applications of the Predict-then-Refine Paradigm
In the era of deep learning, the predict-then-refine paradigm is commonly applied to sequence-to-sequence problems. Tasks such as grammar correction and text rewriting often follow this theme, where an initial sequence is generated and then refined to improve its quality and correctness.
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Computing Sciences
Foundations of Large Language Models Course
Related
Brill's Tagger as an Early Example of Predict-then-Refine
Modern NLP Applications of the Predict-then-Refine Paradigm
Self-Refinement in LLMs
An AI-powered code completion tool is designed to help developers write functions. When a developer provides a function name and a comment describing its purpose, the tool first generates a complete, functional block of code. Following this initial generation, the tool enters a loop where it analyzes the code it just wrote, identifies potential inefficiencies or non-standard practices, and applies a specific correction. This analysis-and-correction loop repeats several times, with the code block being progressively improved at each step. Which statement accurately characterizes the fundamental approach this tool uses?
Distinguishing NLP System Architectures
Analyzing System Architectures for Output Generation
Sequential Scaling
Learn After
An engineering team is building a system to summarize long technical documents. They are considering several architectures. Which of the following designs best exemplifies a 'predict-then-refine' approach for a sequence-to-sequence task?
Improving a Machine Translation System
Evaluating Architectural Choices for Text Style Transfer