NLP, Text Models, Embeddings, and Language Tasks

Natural language processing (NLP)

AI field focused on understanding, interpreting, and generating human language.

Text classification

Assigning text to a category/class, such as spam or not spam.

Naive Bayes

A probabilistic classification algorithm based on Bayes’ theorem with strong independence assumptions.

Naive Bayes model

A probability model used for classification, especially common in simple text classification.

Bayesian classifier

A classifier that uses Bayes’ theorem, priors, and evidence to choose likely classes.

Bag-of-words model

Represents text as an unordered collection of word counts/frequencies, ignoring word order.

Tokenization

Splitting text into smaller units such as words, subwords, or tokens.

Language translation / machine translation

Converting text from one language to another.

Summarization

Condensing longer text into shorter key points; different from classification.

Language model

A model that assigns probabilities to sequences/strings of text.

Corpus

A collection of text or audio data used for analysis/training.

Word embedding

A dense vector representation of word meaning and relationships.

Topical relationship

A relationship based on shared subject area, such as rain and sunshine in weather.

Sentiment relationship

A relationship based on emotional tone, such as sad and angry being negative emotions.

Comparison relationship

A relationship based on degree or comparison, such as tall and taller.

Sound/association relationship

A relationship based on related actions or sensory ideas, such as laugh and smile.