Vector Space Model of Word Representation in NLP
Contributors
- Objectives
- This shortlist will help user the basic concepts of vector semantics, word and vectors, embedding. In addition learn types vector space models namely the tf-idf and Word2vec.
- Potential Use Cases
- Vector space models are used in information filtering, information retrieval, plagiarism detection, news recommender system, comparing, indexing and relevancy rankings of text documents.
- Who is This For ?
- BEGINNERData Scientist new to NLP
Click on each of the following annotated items to see details.
Resource Asset5/7
VIDEO 1. Vector space model
- Quick introduction to vector space model and basic technical concepts
10 minutes
BOOK_CHAPTER 2. TF-IDF
- Technical concepts explained with examples such as term frequency, cosine similarity, inverse document frequency
30 minutes
ARTICLE 3. IF-IDF implementation in python
- How to implement TF-IDF embedding with NLTK in python?
20 minutes
BOOK_CHAPTER 4. Word2Vec
- This section from chapter clearly explains dense semantic model and how Word2Vec model works?
20 minutes
ARTICLE 5. Word2Vec Implementation
- Word2Vec model is implemented from scratch which can help to learn and understand concept clearly.
9 minutes
VIDEO 6. Vector Semanics
- Clear explanation of basic concepts such as word meaning, vectors and embedding with simple examples
15 minutes
BOOK_CHAPTER 7. Lexical Semantics
- Covers basic principles of word meaning required to understand vector semantics, embedding and vector space model
10 minutes
Concepts Covered
0 comment