Implement the Word2Vec Skip-gram model. **Example:** Given a sentence 'the quick brown fox', generate word embeddings. **Constraints:** Use NumPy for efficient computation, assume a fixed vocabulary size.
Test Cases
Test Case 1
Input:
"the quick brown fox", 10, 5Expected:
[[0.1, 0.2, 0.3, 0.4, 0.5], [0.6, 0.7, 0.8, 0.9, 0.1], ...]Test Case 2
Input:
"hello world", 5, 3Expected:
[[0.1, 0.2, 0.3], [0.4, 0.5, 0.6], ...]+ 3 hidden test cases