Transfer learningTransfer learning (TL) is a technique in machine learning (ML) in which knowledge learned from a task is re-used in order to boost performance on a related task. For example, for , knowledge gained while learning to recognize cars could be applied when trying to recognize trucks. This topic is related to the psychological literature on transfer of learning, although practical ties between the two fields are limited. Reusing/transferring information from previously learned tasks to new tasks has the potential to significantly improve learning efficiency.
Feature learningIn machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process.
LearningLearning is the process of acquiring new understanding, knowledge, behaviors, skills, values, attitudes, and preferences. The ability to learn is possessed by humans, animals, and some machines; there is also evidence for some kind of learning in certain plants. Some learning is immediate, induced by a single event (e.g. being burned by a hot stove), but much skill and knowledge accumulate from repeated experiences. The changes induced by learning often last a lifetime, and it is hard to distinguish learned material that seems to be "lost" from that which cannot be retrieved.
Entity linkingIn natural language processing, entity linking, also referred to as named-entity linking (NEL), named-entity disambiguation (NED), named-entity recognition and disambiguation (NERD) or named-entity normalization (NEN) is the task of assigning a unique identity to entities (such as famous individuals, locations, or companies) mentioned in text. For example, given the sentence "Paris is the capital of France", the idea is to determine that "Paris" refers to the city of Paris and not to Paris Hilton or any other entity that could be referred to as "Paris".
Generative pre-trained transformerGenerative pre-trained transformers (GPT) are a type of large language model (LLM) and a prominent framework for generative artificial intelligence. The first GPT was introduced in 2018 by OpenAI. GPT models are artificial neural networks that are based on the transformer architecture, pre-trained on large data sets of unlabelled text, and able to generate novel human-like content. As of 2023, most LLMs have these characteristics and are sometimes referred to broadly as GPTs.
C-commandIn generative grammar and related frameworks, a node in a parse tree c-commands its sister node and all of its sister's descendants. In these frameworks, c-command plays a central role in defining and constraining operations such as syntactic movement, binding, and scope. Tanya Reinhart introduced c-command in 1976 as a key component of her theory of anaphora. The term is short for "constituent command". Common terms to represent the relationships between nodes are below (refer to the tree on the right): M is a parent or mother to A and B.
Learning theory (education)Learning theory describes how students receive, process, and retain knowledge during learning. Cognitive, emotional, and environmental influences, as well as prior experience, all play a part in how understanding, or a worldview, is acquired or changed and knowledge and skills retained. Behaviorists look at learning as an aspect of conditioning and advocate a system of rewards and targets in education.
Transformer (machine learning model)A transformer is a deep learning architecture that relies on the parallel multi-head attention mechanism. The modern transformer was proposed in the 2017 paper titled 'Attention Is All You Need' by Ashish Vaswani et al., Google Brain team. It is notable for requiring less training time than previous recurrent neural architectures, such as long short-term memory (LSTM), and its later variation has been prevalently adopted for training large language models on large (language) datasets, such as the Wikipedia corpus and Common Crawl, by virtue of the parallelized processing of input sequence.
Large language modelA large language model (LLM) is a language model characterized by its large size. Their size is enabled by AI accelerators, which are able to process vast amounts of text data, mostly scraped from the Internet. The artificial neural networks which are built can contain from tens of millions and up to billions of weights and are (pre-)trained using self-supervised learning and semi-supervised learning. Transformer architecture contributed to faster training.
Multiclass classificationIn machine learning and statistical classification, multiclass classification or multinomial classification is the problem of classifying instances into one of three or more classes (classifying instances into one of two classes is called binary classification). While many classification algorithms (notably multinomial logistic regression) naturally permit the use of more than two classes, some are by nature binary algorithms; these can, however, be turned into multinomial classifiers by a variety of strategies.
Named-entity recognitionNamed-entity recognition (NER) (also known as (named) entity identification, entity chunking, and entity extraction) is a subtask of information extraction that seeks to locate and classify named entities mentioned in unstructured text into pre-defined categories such as person names, organizations, locations, medical codes, time expressions, quantities, monetary values, percentages, etc. Most research on NER/NEE systems has been structured as taking an unannotated block of text, such as this one: Jim bought 300 shares of Acme Corp.
Anaphora (linguistics)In linguistics, anaphora (əˈnæfərə) is the use of an expression whose interpretation depends upon another expression in context (its antecedent or postcedent). In a narrower sense, anaphora is the use of an expression that depends specifically upon an antecedent expression and thus is contrasted with cataphora, which is the use of an expression that depends upon a postcedent expression. The anaphoric (referring) term is called an anaphor. For example, in the sentence Sally arrived, but nobody saw her, the pronoun her is an anaphor, referring back to the antecedent Sally.
Pro-formIn linguistics, a pro-form is a type of function word or expression that stands in for (expresses the same content as) another word, phrase, clause or sentence where the meaning is recoverable from the context. They are used either to avoid repetitive expressions or in quantification (limiting the variables of a proposition). Pro-forms are divided into several categories, according to which part of speech they substitute: A pronoun substitutes a noun or a noun phrase, with or without a determiner: it, this.
Recurrent neural networkA recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.
Document classificationDocument classification or document categorization is a problem in library science, information science and computer science. The task is to assign a document to one or more classes or categories. This may be done "manually" (or "intellectually") or algorithmically. The intellectual classification of documents has mostly been the province of library science, while the algorithmic classification of documents is mainly in information science and computer science.
Statistical classificationIn statistics, classification is the problem of identifying which of a set of categories (sub-populations) an observation (or observations) belongs to. Examples are assigning a given email to the "spam" or "non-spam" class, and assigning a diagnosis to a given patient based on observed characteristics of the patient (sex, blood pressure, presence or absence of certain symptoms, etc.). Often, the individual observations are analyzed into a set of quantifiable properties, known variously as explanatory variables or features.
Binding (linguistics)In linguistics, binding is the phenomenon in which anaphoric elements such as pronouns are grammatically associated with their antecedents. For instance in the English sentence "Mary saw herself", the anaphor "herself" is bound by its antecedent "Mary". Binding can be licensed or blocked in certain contexts or syntactic configurations, e.g. the pronoun "her" cannot be bound by "Mary" in the English sentence "Mary saw her". While all languages have binding, restrictions on it vary even among closely related languages.
PluralThe plural (sometimes abbreviated as pl., pl, or ), in many languages, is one of the values of the grammatical category of number. The plural of a noun typically denotes a quantity greater than the default quantity represented by that noun. This default quantity is most commonly one (a form that represents this default quantity of one is said to be of singular number). Therefore, plurals most typically denote two or more of something, although they may also denote fractional, zero or negative amounts.
Self-supervised learningSelf-supervised learning (SSL) is a paradigm in machine learning for processing data of lower quality, rather than improving ultimate outcomes. Self-supervised learning more closely imitates the way humans learn to classify objects. The typical SSL method is based on an artificial neural network or other model such as a decision list. The model learns in two steps. First, the task is solved based on an auxiliary or pretext classification task using pseudo-labels which help to initialize the model parameters.
Grammatical numberIn linguistics, grammatical number is a feature of nouns, pronouns, adjectives and verb agreement that expresses count distinctions (such as "one", "two" or "three or more"). English and other languages present number categories of singular or plural, both of which are cited by using the hash sign (#) or by the numero signs "No." and "Nos." respectively. Some languages also have a dual, trial and paucal number or other arrangements.
