1. Word Embeddings: it refers to the representation of words as real-valued vectors. These vectors capture semantic and syntactic information, allowing computers to understand and process textual content more effectively.

2. NLP (Natural Language Processing): NLP is a field of artificial intelligence that focuses on the interaction between computers and humans using natural language. It involves the development of algorithms and models to enable machines to understand, interpret, and generate human-like text. 

3. Vectorization: is the process of converting words or documents into numeric vectors. In the context of word embeddings, it involves representing words as real-valued vectors in a lower-dimensional space.

4. TF-IDF (Term Frequency-Inverse Document Frequency): TF-IDF is a machine learning algorithm used for word embedding in text. It comprises two metrics, term frequency (TF) and inverse document frequency (IDF), to measure the importance of words in a document or corpus.

5. Bag of Words (BOW): is a word embedding technique where each value in the vector represents the count of words in a document or sentence. It is a method of extracting features from text, disregarding word order.

6. Word2Vec: is a word embedding technique developed by Google. It uses shallow neural networks to learn word representations based on the distributional hypothesis, capturing semantic similarities between words. 

7. GloVe (Global Vectors for Word Representation): GloVe is a word embedding method that focuses on global context to create word representations. It uses a co-occurrence matrix derived from a large corpus to capture semantic relationships between words.

8. BERT (Bidirectional Encoder Representations from Transformers): BERT is a state-of-the-art natural language processing model based on transformers. It utilizes bidirectional attention mechanisms to generate high-quality word embeddings that are contextualized, making it effective for various NLP tasks.