Course Objective & Scope
Customer complaints, call-centre transcripts, survey responses and internal documents live as unstructured text—and in morphologically rich languages like Turkish, suffixes and spelling noise make naive matching brittle. This foundational course covers text cleaning and normalisation, regular expressions, word and subword tokenisation, Bag-of-Words and TF-IDF representations, Word2Vec/FastText and sentence embeddings.
Using spaCy, scikit-learn and ready-to-use Hugging Face pipelines, participants build sentiment/topic classification, Named Entity Recognition (NER) and text similarity workflows, finishing with a fast, interpretable TF-IDF + linear/LightGBM baseline on enterprise-style text.
Who Should Attend?
- Data scientists, software developers and data analysts starting to work with text data
- Technical teams working on customer experience, call-centre, HR and document automation projects
- Engineers building a solid foundation before moving into LLMs and advanced NLP
- Prerequisite: basic Python programming
Key Takeaways
- Build text normalisation pipelines that handle noisy input, encoding quirks and Turkish morphology
- Choose appropriately between word, n-gram and subword tokenisation schemes
- Convert text corpora into numerical matrices using TF-IDF, FastText and sentence embeddings
- Train and evaluate a strong, interpretable text classification baseline in scikit-learn
- Extract people, organisations, dates and key phrases using spaCy and pretrained Hugging Face pipelines
Curriculum
Text Preprocessing, Regex and Turkish Morphology
- Unicode normalisation, stopwords and regex patterns for PII masking
- Agglutinative morphology, stemming/lemmatisation and subword units
Classical Vector Representations: BoW, N-Grams and TF-IDF
- Word and character n-grams for robustness to typos and suffixes
- Working with scikit-learn TfidfVectorizer and sparse matrices
Dense Representations: Word and Sentence Embeddings
- Distributional semantics, Word2Vec and subword-aware FastText
- Sentence embeddings and cosine similarity for nearest-text lookup
Core NLP Tasks: Classification and NER
- Sentiment analysis, ticket routing and intent/topic tagging
- Named Entity Recognition (NER) combining spaCy models and rules
Intro to Hugging Face Pipelines and Baseline Project
- Running off-the-shelf pretrained pipelines and benchmarking against TF-IDF
- Error analysis and a reusable working example on the enterprise case
Other Courses in This Category
-
Advanced NLP under scarce labels: domain-adaptive pretraining (MLM), DeBERTa/RoBERTa fine-tuning, LoRA/PEFT, few-shot learning with SetFit, weak supervision and label cleaning (Cleanlab), long documents and cross-lingual transfer.
- Live Course
- 5 modules
-
End-to-end neural NLP covering subword tokenisation, BiLSTM-CRF and Transformer (BERT, DeBERTa, T5) architectures, with hands-on sequence tagging, seq2seq summarisation and question answering in PyTorch and Hugging Face.
- Live Course
- 5 modules
-
Running NLP models in production at low latency and cost: ONNX/Optimum quantisation, Triton/FastAPI serving, dynamic batching, PII redaction (Presidio), behavioural testing (CheckList) and text drift monitoring.
- Live Course
- 5 modules
-
Turning unstructured documents into structured tables and JSON: hierarchical and multi-label classification, GLiNER and Transformer NER, relation and event extraction, layout-aware PDF parsing and schema-validated extraction.
- Live Course
- 5 modules
-
Enterprise search beyond keyword matching: Sentence-Transformers (bi-encoders), multilingual embeddings, BM25/SPLADE + dense hybrid retrieval, Reciprocal Rank Fusion, Cross-Encoder reranking, Qdrant/pgvector and NDCG@k evaluation.
- Live Course
- 5 modules
-
Deep Learning with PyTorch
Comprehensive deep learning training with PyTorch 2.x covering tensor operations, autograd, CNNs, Transformers, LLM fine-tuning (LoRA/QLoRA), diffusion models, GNNs, and production deployment.
- Live Course
- 12 modules
Get in touch
