Google
PROFESSIONAL-DATA-ENGINEER · Question #211
You work on a regression problem in a natural language processing domain, and you have 100M labeled exmaples in your dataset. You have randomly shuffled your data and split your dataset into train…
The correct answer is D. Increase the complexity of your model by, e.g., introducing an additional layer or increase sizing the size of vocabularies or n-grams used. Explanation/Reference: This is a case of underfitting - not overfitting (for over fitting the model will have extremely low training error but a high testing error) - so we need to make the model more complex - answer is D.
Submitted by layla.eg· Mar 30, 2026Operationalizing machine learning models
Question
You work on a regression problem in a natural language processing domain, and you have 100M labeled exmaples in your dataset. You have randomly shuffled your data and split your dataset into train and test samples (in a 90/10 ratio). After you trained the neural network and evaluated your model on a test set, you discover that the root-mean-squared error (RMSE) of your model is twice as high on the train set as on the test set. How should you improve the performance of your model?
Options
- AIncrease the share of the test sample in the train-test split.
- BTry to collect more data and increase the size of your dataset.
- CTry out regularization techniques (e.g., dropout of batch normalization) to avoid overfitting.
- DIncrease the complexity of your model by, e.g., introducing an additional layer or increase sizing the size of vocabularies or n-grams used.
How the community answered
(29 responses)- A24% (7)
- B10% (3)
- C3% (1)
- D62% (18)
Explanation
Explanation/Reference: This is a case of underfitting - not overfitting (for over fitting the model will have extremely low training error but a high testing error) - so we need to make the model more complex - answer is D.
Topics
#model underfitting#RMSE#model complexity#NLP regression
Community Discussion
No community discussion yet for this question.