Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn named entity recognition (NER) techniques in Python specifically designed for digital humanities research through this comprehensive video series. Master the fundamentals of natural language processing and information extraction to transform unstructured texts into structured data without requiring prior machine learning knowledge. Explore both rules-based and machine learning approaches to NER using spaCy and Gensim libraries, progressing from basic concepts to advanced model training and customization. Discover how to implement spaCy's EntityRuler, create custom training datasets, and train specialized NER models for humanities research. Delve into word vectors and their mathematical representations, learning to generate custom word vectors with Gensim and integrate them into spaCy models. Navigate the transition from spaCy 2x to 3x, understanding pipeline management, custom factories, and configuration files. Practice with real-world applications including Holocaust-related entity recognition and Classical Latin text processing. Develop skills in model evaluation using confusion matrices, precision and recall metrics, and both formal and informal testing methodologies. Build expertise in creating domain-specific NER pipelines tailored to digital humanities research needs, from data preparation through model deployment and performance assessment.
