Pure Language Processing with Probabilistic Fashions

About this Course

In Course 2 of the Pure Language Processing Specialization, you’ll:

a) Create a easy auto-correct algorithm utilizing minimal edit distance and dynamic programming, b) Apply the Viterbi Algorithm for part-of-speech (POS) tagging, which is important for computational linguistics, c) Write a greater auto-complete algorithm utilizing an N-gram language mannequin, and d) Write your individual Word2Vec mannequin that makes use of a neural community to compute phrase embeddings utilizing a steady bag-of-words mannequin. By the top of this Specialization, you’ll have designed NLP functions that carry out question-answering and sentiment evaluation, created instruments to translate languages and summarize textual content, and even constructed a chatbot! This Specialization is designed and taught by two specialists in NLP, machine studying, and deep studying. Younes Bensouda Mourri is an Teacher of AI at Stanford College who additionally helped construct the Deep Studying Specialization. Łukasz Kaiser is a Employees Analysis Scientist at Google Mind and the co-author of Tensorflow, the Tensor2Tensor and Trax libraries, and the Transformer paper.

WHAT YOU WILL LEARN

• Use dynamic programming, hidden Markov fashions, and phrase embeddings to implement autocorrect, autocomplete & determine part-of-speech tags for phrases.

   

SKILLS YOU WILL GAIN

• Word2vec
• Components-of-Speech Tagging
• N-gram Language Fashions
• Autocorrect

Syllabus – What you’ll be taught from this course

Content material Score91%(6,108 scores)

WEEK

1

7 hours to finish

Autocorrect

Find out about autocorrect, minimal edit distance, and dynamic programming, then construct your individual spellchecker to right misspelled phrases!

WEEK

2

6 hours to finish

A part of Speech Tagging and Hidden Markov Fashions

Find out about Markov chains and Hidden Markov fashions, then use them to create part-of-speech tags for a Wall Road Journal textual content corpus!

WEEK

3

9 hours to finish

Autocomplete and Language Fashions

Find out about how N-gram language fashions work by calculating sequence chances, then construct your individual autocomplete language mannequin utilizing a textual content corpus from Twitter!

WEEK

4

9 hours to finish

Phrase embeddings with neural networks

Find out about how phrase embeddings carry the semantic which means of phrases, which makes them rather more highly effective for NLP duties, then construct your individual Steady bag-of-words mannequin to create phrase embeddings from Shakespeare textual content.