Term frequency-inverse document frequency is a means of assigning weight to a search term when comparing individual documents within a corpus. It is an improvement on the bag-of-words model in that it considers the relative rarity of a term within a larger corpus.

• information retrieval
• linguistics
• nlp
• reference

The bag-of-words (BoW) model is used to represent a document as a fixed-length vector of frequency counts for each token in the document. BoW models are useful in classification, machine learning, and topic modeling tasks, among others.

• information retrieval
• linguistics
• nlp
• reference

In natural language processing, stemming is the process of reducing a word to its stem form. Typically, stemming is used as part of an NLP pipeline in order to reduce all words in a text to their stems so that they can be analyzed together.

• linguistics
• nlp
• nltk
• reference

A word stem is the form of a word that can accept affixes (suffixes and prefixes) and is thus common to all inflected variants.

• linguistics
• reference

A root word is a word with no prefixes or suffixes, meaning that it is the primary lexical unit of a set of words and represents the principle semantic meaning of the set.

• linguistics
• reference

Lemmatization is the process of reducing a word to its lemma (canonical form). In natural language processing, a lemmatizer may be used to reduce all words in a given text to their lemmas, which makes comparative analysis possible based on canonical forms.

• gensim
• linguistics
• nlp
• nltk
• reference
• spacy

A rectified linear unit (ReLU) is an activation function that outputs the input directly if the input is positive, and otherwise outputs zero.

• deep learning
• neural networks
• reference

Back-propagation is an algorithm used during the training process of a feedforward neural network.

• deep learning
• neural networks
• reference

A feedforward neural network (aka multilayer perceptron or deep feedforward network) is a supervised learning network in which information only flows forward.

• deep learning
• neural networks
• reference

Loss functions are used to quantify to what extent a prediction was right/wrong (rather than simply if it was right or wrong.) The purpose of a loss function is to work as part of the optimization process to update a neural network so that it reaches the desired result.

• deep learning
• neural networks
• reference