BERT_Word_Embeddings: Explain what is google BERT, what is the difference between BERT Embedding and Word2Vec-embedding, step by step to transform data, tokenizer and build the word vector from hidden layers and compute cosine similarity between 2 sentences containing the same word
-
chapter 1: Introduce you to the basics of text processing with spaCy: data structures, statistical models, and how to use them to predict linguistic features in your text.
-
chapter 2: Extract specific information from large volumes of text, to make the most of spaCy's data structures and to combine statistical and rule-based approaches for text analysis.
-
Named Entity Recognition: Apply Named Entity Recoginiton and spaCy pretrained model on finance news.
-
Conversation AI: Rasa Open Source
-
NLP/NLU Open Souce: SpaCy, Element AI
-
Text processing : TextHero
-
Text similarity calculation: FuzzyWuzzy