Learn Before
Checking Whether a Translation Error Comes from Search or Scoring
For a translation system, assign a score to candidate outputs and use approximate search, since the number of possible sentences is too large for exact search. If a reference translation receives a higher score than the system’s chosen output, the search procedure is likely responsible for the error. If the system output still scores at least as well as the reference, the scoring function is the more likely problem.
0
1
Tags
Data Science
Foundations of Large Language Models Course
Computing Sciences
D2L
Dive into Deep Learning @ D2L
Machine Learning
Deep Learning
Supervised Learning
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Related
Classifying development-set mistakes with optimization verification
Approximate Scoring Followed by Approximate Search
Checking Whether a Translation Error Comes from Search or Scoring
Checking Reward Quality in Reinforcement Learning
A useful human output for optimization verification
What does this optimization check suggest when the reference candidate scores higher than the algorithm’s output?
Using the Optimization Verification Test
Optimization Check Symbols
How to carry out an optimization verification check
Using the Optimization Verification Check
Debugging a Translation Decoder
When to Attribute an Error to Optimization
When Is an Optimization Check Useful?
Checking the Source of a Performance Problem
Optimization checks can isolate the source of a training problem
Learn After
Diagnosing a decoding error
Can Exhaustive Search Handle Very Large Route Spaces?
A large candidate space often requires _____ Search.
Match the score comparison to the likely cause.
Order the steps for diagnosing a bad recommendation in a score-based selection system.
Why Compare Scores During Translation Error Diagnosis?
Finding a Fault in a Translation Score
Why Translation Candidates Receive Scores
Where Did the Ranking Error Come From?
Search Procedure Failure Condition