Module 1: Introduction to NLP and Text Preprocessing

• Defining NLP, its history, and key application areas (e.g., Sentiment Analysis, Translation)
• The process of Tokenization (word, character, and sub-word tokenization)
• Techniques for Cleaning Text Data (noise removal, casing, and normalization)
• Stemming (e.g., Porter Stemmer) versus Lemmatization (e.g., WordNet Lemmatizer)
• Practical session: Building a Python Text Preprocessing Pipeline using the NLTK and spaCy libraries

Module 2: Linguistic Fundamentals and Feature Engineering

• Part-of-Speech (POS) Tagging and its role in syntactic analysis
• Named Entity Recognition (NER) for extracting key entities (people, places, organizations)
• Feature Vectorization: Count Vectorizer (Bag-of-Words) and Term Frequency-Inverse Document Frequency (TF-IDF)
• Handling sparsity and high dimensionality in text feature vectors
• Practical session: Implementing Feature Vectorization (Bag-of-Words and TF-IDF) and comparing their performance

Module 3: Statistical Language Modeling

• Core concepts of Language Modeling: Calculating the probability of a word sequence
• N-gram Models: Unigrams, Bigrams, and Trigrams for sequence prediction
• The challenge of Data Sparsity and the need for Smoothing techniques (e.g., Laplace smoothing)
• Perplexity as the primary evaluation metric for language models
• Practical session: Building and evaluating an N-gram Language Model for text prediction and generation

Module 4: Machine Learning for Text Classification

• The application of Supervised Learning to classification tasks (e.g., spam detection, topic categorization)
• Training and optimizing the Naive Bayes Classifier for text data
• Using Support Vector Machines (SVM) for text classification and high-dimensional features
• Cross-validation and standard evaluation metrics (Accuracy, Precision, Recall, F1-Score)
• Practical session: Implementing and comparing Naive Bayes and SVM for a movie review sentiment analysis task

Module 5: Deep Learning Fundamentals for NLP

• Introduction to Neural Networks and the concept of sequential data processing
• Recurrent Neural Networks (RNNs) and their limitations (vanishing gradient problem)
• Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) to manage long-term dependencies
• Training sequences: Batching, padding, and masking techniques
• Practical session: Developing an LSTM-based model for classifying sequential text data (e.g., identifying toxic comments)

Module 6: Word Embeddings and Vector Representations

• Moving from discrete symbols to dense vector representations
• Conceptual foundation of Distributional Semantics and the "Word as Context" idea
• Skip-gram and Continuous Bag-of-Words (CBOW) models in Word2Vec
• Advanced Embedding Techniques: GloVe and FastText, and their differences
• Practical session: Training custom Word2Vec embeddings on a large text corpus and visualizing semantic clusters

Module 7: Sequence-to-Sequence Models and Attention

• The Encoder-Decoder architecture for Sequence-to-Sequence (Seq2Seq) tasks (e.g., Machine Translation)
• Beam Search and Greedy Decoding strategies for generating output sequences
• The critical role of the Attention Mechanism in overcoming information bottleneck and improving long-range dependencies
• Implementing Seq2Seq for language generation and summarizing short texts
• Practical session: Building a basic Seq2Seq model with an Attention layer for a simple English-to-French translation task

Module 8: The Transformer Architecture and BERT

• Deconstructing the Transformer: The shift from recurrence to parallel processing
• Detailed understanding of the Multi-Head Self-Attention mechanism and Positional Encodings
• Introduction to Pre-trained Language Models: The Masked Language Modeling task (MLM)
• Fine-tuning BERT (Bidirectional Encoder Representations from Transformers) for downstream tasks
• Practical session: Fine-tuning a pre-trained BERT model from the Hugging Face library for a Named Entity Recognition task

Module 9: Advanced NLP Applications

• Abstractive vs. Extractive Text Summarization techniques and model selection
• Building Question Answering (Q&A) systems using both retrieval and extractive methods
• Advanced Machine Translation challenges and multi-lingual model training
• Introduction to Generative Pre-trained Transformer (GPT) models and prompting techniques
• Practical session: Implementing an extractive Question Answering model on a document dataset

Module 10: Ethics, Bias, and Deployment in NLP

1. Identifying and mitigating societal biases (gender, race) embedded in training data and embeddings
2. Methods for Model Interpretability (e.g., SHAP values) to understand model decisions
3. Strategies for deploying NLP models as REST APIs using frameworks like Flask or FastAPI
4. Monitoring model drift and maintaining performance in production environments
5. Practical session: Analyzing a pre-trained model for bias using fairness metrics and implementing a basic model deployment stub

Requirements:

·       Participants should be reasonably proficient in English.

·       Applicants must live up to Armstrong Global Institute admission criteria.

Terms and Conditions

1. Discounts: Organizations sponsoring Four Participants will have the 5th attend Free

2. What is catered for by the Course Fees: Fees cater for all requirements for the training – Learning materials, Lunches, Teas, Snacks and Certification. All participants will additionally cater for their travel and accommodation expenses, visa application, insurance, and other personal expenses.

3. Certificate Awarded: Participants are awarded Certificates of Participation at the end of the training.

4. The program content shown here is for guidance purposes only. Our continuous course improvement process may lead to changes in topics and course structure.

5. Approval of Course: Our Programs are NITA Approved. Participating organizations can therefore claim reimbursement on fees paid in accordance with NITA Rules.

Booking for Training

Simply send an email to the Training Officer on training@armstrongglobalinstitute.com and we will send you a registration form. We advise you to book early to avoid missing a seat to this training.

Or call us on +254720272325 / +254725012095 / +254724452588

Payment Options

We provide 3 payment options, choose one for your convenience, and kindly make payments at least 5 days before the Training start date to reserve your seat:

1. Groups of 5 People and Above – Cheque Payments to: Armstrong Global Training & Development Center Limited should be paid in advance, 5 days to the training.

2. Invoice: We can send a bill directly to you or your company.

3. Deposit directly into Bank Account (Account details provided upon request)

Cancellation Policy

1. Payment for all courses includes a registration fee, which is non-refundable, and equals 15% of the total sum of the course fee.

2. Participants may cancel attendance 14 days or more prior to the training commencement date.

3. No refunds will be made 14 days or less before the training commencement date. However, participants who are unable to attend may opt to attend a similar training course at a later date or send a substitute participant provided the participation criteria have been met.

Tailor Made Courses

This training course can also be customized for your institution upon request for a minimum of 5 participants. You can have it conducted at our Training Centre or at a convenient location. For further inquiries, please contact us on Tel: +254720272325 / +254725012095 / +254724452588 or Email training@armstrongglobalinstitute.com

Accommodation and Airport Transfer

Accommodation and Airport Transfer is arranged upon request and at extra cost. For reservations contact the Training Officer on Email: training@armstrongglobalinstitute.com or on Tel: +254720272325 / +254725012095 / +254724452588