Lec 08 | Word Representation: GloVe

This video presentation explores the GloVe model's innovative methodology that effectively combines count-based and prediction-based techniques for learning word representations, illuminating the significant advancements in the field of NLP. 🎓 Lecturer: Tanmoy Chakraborty [https://tanmoychak.com] 🔗 Get the Book: https://tanmoychak.com/llmbook 📚 Suggested Readings: - GloVe: Global Vectors for Word Representation [https://aclanthology.org/D14-1162.pdf] - Chapter-3, Intro to LLM, Word Embedding: Sections 3.3.3 (Global Vectors for Word Representation)[https://tanmoychak.com/llmbook/] 📚 Optional Readings on Bias Captured by Word Embeddings: - Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings [https://papers.nips.cc/paper_files/paper/2016/file/a486cd07e4ac3d270571622f4f316ec5-Paper.pdf] - Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change [https://aclanthology.org/P16-1141.pdf] - Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes [https://arxiv.org/pdf/1711.08412] In this lecture, the approach of combining count-based and prediction-based methods in word representation through the GloVE model. This lecture offers an in-depth exploration of GloVe, or Global Vectors, which provides a robust framework for word embeddings. Perfect for students and researchers aiming to enhance their understanding of semantic representation in NLP, this session bridges the gap between theoretical concepts and practical applications.