rohitg00--ai-engineering-from-scratch
wehub-resource-sync
103 行
3.9 KiB
JSON
103 行
3.9 KiB
JSON
{
|
|
"lesson": "05-sentiment-analysis",
|
|
"title": "Sentiment Analysis",
|
|
"questions": [
|
|
{
|
|
"stage": "pre",
|
|
"question": "Why is 'The food was not great' a hard case for naive BoW classifiers?",
|
|
"options": [
|
|
"It has no punctuation",
|
|
"It mixes English and French",
|
|
"Negation flips meaning, but bag of words discards the link between 'not' and 'great'",
|
|
"It contains too few tokens"
|
|
],
|
|
"correct": 2,
|
|
"explanation": "BoW cannot bind 'not' to the word it negates, so the classifier misses the polarity flip."
|
|
},
|
|
{
|
|
"stage": "pre",
|
|
"question": "What two steps make up classical sentiment analysis?",
|
|
"options": [
|
|
"Translate, then classify",
|
|
"Embed, then cluster",
|
|
"Represent (vectorize text) and classify (linear model on the vector)",
|
|
"Search, then rank"
|
|
],
|
|
"correct": 2,
|
|
"explanation": "Classical sentiment is feature extraction followed by a linear classifier."
|
|
},
|
|
{
|
|
"stage": "check",
|
|
"question": "Why does Naive Bayes work despite its 'naive' independence assumption?",
|
|
"options": [
|
|
"With sparse text features and moderate data the classifier mostly cares which side each word leans toward, not exact joint probabilities",
|
|
"Naive Bayes secretly learns interactions",
|
|
"The assumption is actually true for text",
|
|
"Laplace smoothing fixes dependence"
|
|
],
|
|
"correct": 0,
|
|
"explanation": "Even with wrong independence, leaning-direction information per word is enough to classify well."
|
|
},
|
|
{
|
|
"stage": "check",
|
|
"question": "Why include 'NOT_' prefixed tokens during preprocessing?",
|
|
"options": [
|
|
"To normalize case",
|
|
"To stem the words",
|
|
"To turn 'good' versus 'NOT_good' into separate features that the classifier can weight oppositely",
|
|
"To shrink the vocabulary"
|
|
],
|
|
"correct": 2,
|
|
"explanation": "Negation scoping splits negated forms into distinct features so a BoW classifier can model the flip."
|
|
},
|
|
{
|
|
"stage": "check",
|
|
"question": "Why is removing stopwords risky for sentiment analysis?",
|
|
"options": [
|
|
"Negation words ('not', 'no', 'never') are usually treated as stopwords but carry sentiment signal",
|
|
"Stopword lists are too long",
|
|
"It increases sparsity",
|
|
"Stopword removal breaks tokenization"
|
|
],
|
|
"correct": 0,
|
|
"explanation": "Default stopword lists drop negations and similar carriers of sentiment."
|
|
},
|
|
{
|
|
"stage": "post",
|
|
"question": "Which metric should you report when sentiment classes are imbalanced?",
|
|
"options": [
|
|
"Macro-F1 (mean of per-class F1s, equal-weighted)",
|
|
"Accuracy alone",
|
|
"Mean squared error",
|
|
"Micro-F1 only"
|
|
],
|
|
"correct": 0,
|
|
"explanation": "Macro-F1 forces the minority class to count; accuracy or micro-F1 hides it."
|
|
},
|
|
{
|
|
"stage": "post",
|
|
"question": "When should you skip classical models and reach for a transformer for sentiment?",
|
|
"options": [
|
|
"When you have under 100 examples",
|
|
"When latency is critical",
|
|
"When you need explainability",
|
|
"Sarcasm detection, long shifting documents, aspect-based sentiment, or low-resource languages"
|
|
],
|
|
"correct": 3,
|
|
"explanation": "Sarcasm, aspect-based, and cross-lingual sentiment exceed classical BoW models' reach."
|
|
},
|
|
{
|
|
"stage": "post",
|
|
"question": "Why is L2 regularization important for logistic regression on text?",
|
|
"options": [
|
|
"Required to compute gradients",
|
|
"Avoids ReLU dead units",
|
|
"Speeds up matrix inversion",
|
|
"Sparse high-dimensional text features otherwise let the model memorize training examples"
|
|
],
|
|
"correct": 3,
|
|
"explanation": "L2 prevents overfitting in the sparse-feature, high-dimensional regime of text."
|
|
}
|
|
]
|
|
}
|