Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn natural language processing (NLP) techniques using spaCy, a powerful Python library designed for digital humanities applications. Master the fundamentals of spaCy through hands-on tutorials covering installation, data cleaning, and text preprocessing. Explore core NLP concepts including sentence segmentation, named entity recognition (NER), part-of-speech tagging, and lemmatization to extract meaningful information from textual data. Discover how to identify and extract specific linguistic elements such as nouns, noun chunks, verbs, and verb phrases from your texts. Develop skills in data visualization using DisplaCy to create visual representations of linguistic structures and customize these visualizations for your specific research needs. Delve into advanced named entity recognition techniques, including machine learning approaches and custom entity training using spaCy's EntityRuler. Understand the principles of word vectors and learn to generate custom word embeddings using Gensim, then integrate them into spaCy models for enhanced text analysis. Build custom NER pipelines tailored to specific domains, such as Holocaust studies and Classical Latin texts, while mastering precision and recall evaluation metrics. Navigate the transition from spaCy 2.x to 3.x, learning new pipeline architectures, custom factories, and configuration file management. Explore specialized applications including text classification with Classy Classification, coreference resolution, weak supervision techniques with Skweak, and prepositional phrase extraction. Master advanced features like SpanCat for span categorization, document serialization with DocBin, and the integration of multiple NLP models into comprehensive processing pipelines. Gain practical experience with real-world projects and annotation workflows using tools like Prodigy for efficient model training and evaluation.
