Inventing Curriculum using Python and spaCy
summary
A concrete pipeline builds a dataset from job postings and written syllabi, cleans text (stopword removal, lemmatization, lowercase), computes top-10 unigrams/bigrams/trigrams, and compares them to syllabus items; tools include spaCy and textacy with scikit-learn for modeling and a pointer-generator network to combine extractive and abstractive summaries. Preprocessing cuts token counts dramatically; the prototype finds only 5 unigram matches and 1 bigram match in top-10 lists and either recommends adding keywords or proposing a new course.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 2:07Engineering curricula in India
- 5:41Syllabus vs job needs
- 8:11Text summarization techniques
- 12:10spaCy features
- 14:20textacy for spaCy
- 16:25Code walkthrough
- 22:09Output analysis
- 24:16Conclusion
related talks
01h 29mTricks, tips and topics in Text Analysis
01h 27mTips, Tricks and Topics in Text Analysis
48mTopic Modelling (and more) with NLP framework Gensim
01h 38mNavigating the World of NLP and Text Analytics
44mTeaching Computers ABCs: A Quick Intro to Natural Language Processing
21mPersonalization of Programming Education: An NLP-based Bi-dimensional(…)
01h 14mIntroduction to NLP
43mGetting started with AI for free