Course Summary
Learn the basics of natural language processing and explore how to use Python libraries for text analysis and manipulation.Key Learning Points
- Understand the fundamentals of natural language processing
- Learn how to clean and preprocess text data
- Practice using Python libraries for text analysis and manipulation
Related Topics for further study
Learning Outcomes
- Understand the basics of natural language processing
- Learn how to use Python libraries for text analysis and manipulation
- Be able to clean and preprocess text data for analysis
Prerequisites or good to have knowledge before taking this course
- Basic knowledge of Python programming
- Understanding of basic statistics and machine learning concepts
Course Difficulty Level
IntermediateCourse Format
- Online
- Self-paced
Similar Courses
- Applied Natural Language Processing
- Text Mining and Analytics
Related Education Paths
Notable People in This Field
- Jacob Perkins
- Dan Jurafsky
Related Books
Description
This course covers a wide range of tasks in Natural Language Processing from basic to advanced: sentiment analysis, summarization, dialogue state tracking, to name a few. Upon completing, you will be able to recognize NLP tasks in your day-to-day work, propose approaches, and judge what techniques are likely to work well. The final project is devoted to one of the most hot topics in today’s NLP. You will build your own conversational chat-bot that will assist with search on StackOverflow website. The project will be based on practical assignments of the course, that will give you hands-on experience with such tasks as text classification, named entities recognition, and duplicates detection.
Outline
- Intro and text classification
- About the University
- About this course
- Welcome video
- Main approaches in NLP
- Brief overview of the next weeks
- [Optional] Linguistic knowledge in NLP
- Text preprocessing
- Feature extraction from text
- Linear models for sentiment analysis
- Hashing trick in spam filtering
- Neural networks for words
- Neural networks for characters
- About University
- Rules on the academic integrity in the course
- Prerequisites check-list
- Hardware for the course
- Getting started with practical assignments
- Classical text mining
- Simple neural networks for text
- Language modeling and sequence tagging
- Count! N-gram language models
- Perplexity: is our model surprised with a real text?
- Smoothing: what if we see new n-grams?
- Hidden Markov Models
- Viterbi algorithm: what are the most probable tags?
- MEMMs, CRFs and other sequential models for Named Entity Recognition
- Neural Language Models
- Whether you need to predict a next word or a label - LSTM is here to help!
- Perplexity computation
- Probabilities of tag sequences in HMMs
- Language modeling
- Sequence tagging with probabilistic models
- Vector Space Models of Semantics
- Distributional semantics: bee and honey vs. bee an bumblebee
- Explicit and implicit matrix factorization
- Word2vec and doc2vec (and how to evaluate them)
- Word analogies without magic: king – man + woman != queen
- Why words? From character to sentence embeddings
- Topic modeling: a way to navigate through text collections
- How to train PLSA?
- The zoo of topic models
- Word and sentence embeddings
- Topic Models
- Sequence to sequence tasks
- Introduction to Machine Translation
- Noisy channel: said in English, received in French
- Word Alignment Models
- Encoder-decoder architecture
- Attention mechanism
- How to deal with a vocabulary?
- How to implement a conversational chat-bot?
- Sequence to sequence learning: one-size fits all?
- Get to the point! Summarization with pointer-generator networks
- Introduction to machine translation
- Encoder-decoder architectures
- Summarization and simplification
- Dialog systems
- Task-oriented dialog systems
- Intent classifier and slot tagger (NLU)
- Adding context to NLU
- Adding lexicon to NLU
- State tracking in DM
- Policy optimisation in DM
- Final remarks
- Instructions for Telegram bot hosted on AWS [Optional]
- Papers mentioned in week 5
- Keep up-to-date with NLP research
- Task-oriented dialog systems
Summary of User Reviews
Pros from User Reviews
- Well-structured lectures and assignments
- Engaging and knowledgeable instructors
- Practical exercises and projects that reinforce learning
- Real-world applications and case studies
- Access to a supportive and active online community
Cons from User Reviews
- Some students found the course to be too technical or challenging
- Limited opportunities for personalized feedback
- Not enough emphasis on certain topics like machine learning
- Some technical issues reported with the online platform
- Course material may become outdated quickly due to the fast-paced nature of the field
Anna Potapenko
4.4 Raiting
Python - Text Processing for Beginners
- 3.7
-
![]()
![]()
![]()
![]()
![]()
This course quickly allow you to understand the concepts and start writing Python text processing using NLTK ,. This course will cover Python from basics with examples....
Kaggle Masterclass - build a Data Science Portfolio
- 3.5
-
![]()
![]()
![]()
![]()
![]()
Become a Kaggle Grandmaster, build a compelling Data Science portfolio, and take your career to the next level. And the best platform for a Data Scientist is Kaggle!...
Implementing Deep Learning Algorithms with TensorFlow 2.0
- 3.8
-
![]()
![]()
![]()
![]()
![]()
Build and train Deep Learning neural networks with TensorFlow 2. Deep Learning has caused the revival of Artificial Intelligence. 0. About the Author...
Applying Machine Learning to your Data with GCP 日本語版
- 0.0
-
![]()
![]()
![]()
![]()
![]()
ペタバイト規模のデータに対して数秒でクエリを実行して処理する方法や、データの増大に合わせて自動的にスケーリングされるデータ分析に関心がある場合は、ぜひ Data Insights コースを受講してください。 この 1 週間のオンライン速習コースに参加すると、Google Cloud Platform を使用したデータ分析と可視化によって分析情報を得る方法を学習できます。本コースにはインタラクティブなシナリオとハンズオンラボが用意されており、参加者は Google BigQuery のさまざまなデータセットを使用して、分析情報の探索、マイニング、読み込み、可視化、抽出を行うことができます。本コースでは、データの読み込み、クエリの実行、スキーマのモデル化、パフォーマンスの最適化、クエリの料金、データの可視化を扱います。 前提条件 本コースを最大限に活用するには、この専門講座で以下のコースを事前に完了する必要があります。 • Exploring and Preparing your Data...
