0% completed

All LessonsFree Lessons (7)

What you'll learn from this course

Word Embeddings

Embedding Matrix

Candidate Sampling

Cosine Similarity

K-Nearest Neighbors

Language Model

Introduction Language Model Padding RNN/LSTM Dropout Multiple Layers LSTM Output Calculating Loss Predictions Tensor Indexing Quiz

Text Classification

Introduction Sentiment Analysis Embeddings Bidirectional LSTM Logits Loss Classification Improving the Model Quiz

Seq2Seq Model

Introduction Training Data Final States Combined State Encoder-Decoder Attention Training Sampler Decoder Object Decoding Output Calculating Loss Inference Decoding Model Improvement Datasets Quiz Course Conclusion

Fundamentals of NLP

Natural Language Processing with Machine Learning/

...

/

Quiz

Quiz

We'll cover the following...

Technical Quiz

1.

Why do we use word embeddings?

A.

They’re used to represent a sequence of words as a single continuous vector

B.

Word embeddings are easier to look up than regular tokenized IDs

C.

It makes training models for NLP tasks quicker and more efficient

D.

As a more meaningful way to capture the connections between vocabulary words

1 / 4