BART Model's Use of Diverse Input Corruption Methods
After defining the model architecture and training objective for a denoising autoencoder, a key remaining step is to specify how the input data is corrupted. The BART model, developed by Lewis et al. (2020), exemplifies this by employing several different methods for corrupting the input sequence during its pre-training phase.
0
1
Tags
Ch.1 Pre-training - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Related
Example of Denoising Task with Consecutive Token Masking
Span-Based Denoising as an Encoder-Decoder Training Objective
Input Corruption Methods for Denoising Autoencoder Training
Denoising Autoencoder Training Objective
Loss Calculation for Encoder-Decoder Denoising Tasks
Training Efficiency in Denoising Autoencoding
Flexibility of Masked Language Modeling for Encoder-Decoder Training
Example of a Denoising Autoencoder Task for Encoder-Decoder Models
BART Model's Use of Diverse Input Corruption Methods
An encoder-decoder model is being trained using the following example:
- Input to Encoder: "The scientist carefully [MASK] the solution into the beaker."
- Target Output for Decoder: "The scientist carefully poured the solution into the beaker."
Based on this training setup, what is the primary function of the decoder?
Evaluating a Model Training Objective
An encoder-decoder model is being trained with the objective of reconstructing a full, original sentence from an input version where several random words have been removed. What is the most critical function of the encoder's output in this specific training paradigm?
Corrupted Input for Encoder-Decoder Pre-training
Diagrammatic Example of an Encoder-Decoder Model Trained with a Denoising Autoencoding Objective
Learn After
Diagnosing a Denoising Pre-training Strategy
A research team is pre-training a text-based model with the goal of making it highly robust and flexible for a wide range of downstream applications, including generating coherent paragraphs and correcting grammatical errors. The model is trained to reconstruct original text from a corrupted version. Which of the following corruption strategies applied during pre-training would be most effective for achieving this goal?
Analysis of Input Corruption Techniques