Delve deeper into fully enhancing Token Classification by understanding linguistic and semantic aspects of Natural Language Processing. Gain grasp of language morphology and recognize entity types using spaCy.
Overview
Syllabus
- Unit 1: Exploring Syntactic Dependencies and Token Shapes in NLP
- Filtering Syntactic Dependencies and Token Shapes
- Filtering Specific Syntactic Dependencies and Token Shapes
- Creating Sentence with Unique Dependency and Shape
- Syntactic Dependencies and Token Shapes Filtering
- Filtering Syntactic Dependencies and Numerically Initiated Token Shapes
- Unit 2: Understanding Semantic Similarity in NLP with spaCy
- Semantic Similarity with Custom Sentences
- Semantic Similarity Between Two Specific Sentences
- Semantic Similarity Between Unrelated Sentences
- Finding the Most Dissimilar Sentences
- Unit 3: Recognizing Language Morphology for Advanced Token Classification in NLP Using spaCy
- Extracting Specific Morphological Features for Verbs
- Extract Number Feature from Noun Tokens
- Create a Sentence with Specific Morphological Features
- Discovering Feature-Rich Sentence in Text Analysis
- Unit 4: Unveiling the Essentials of Entity Recognition with spaCy
- Filtering Out Organization Entities
- Identifying Specific Entities in Custom Text
- Extracting 'ORG' and 'GPE' Entities with Spacy
- Unique Geopolitical Entities in Reuters Dataset
- Unit 5: Expanding the spaCy NLP Pipeline with Custom Components
- Modify Phonetic Key Function in spaCy
- Implement Verb Count Pipeline Component
- Creating a Vowel Detection Custom Extension in spaCy
- Implement Same POS Counting Pipeline Component