Natural language generationNatural language generation (NLG) is a software process that produces natural language output. A widely-cited survey of NLG methods describes NLG as "the subfield of artificial intelligence and computational linguistics that is concerned with the construction of computer systems than can produce understandable texts in English or other human languages from some underlying non-linguistic representation of information". While it is widely agreed that the output of any NLG process is text, there is some disagreement about whether the inputs of an NLG system need to be non-linguistic.
DialogueDialogue (sometimes spelled dialog in American English) is a written or spoken conversational exchange between two or more people, and a literary and theatrical form that depicts such an exchange. As a philosophical or didactic device, it is chiefly associated in the West with the Socratic dialogue as developed by Plato, but antecedents are also found in other traditions including Indian literature. The term dialogue stems from the Greek διάλογος (dialogos, conversation); its roots are διά (dia: through) and λόγος (logos: speech, reason).
Dialogue systemA dialogue system, or conversational agent (CA), is a computer system intended to converse with a human. Dialogue systems employed one or more of text, speech, graphics, haptics, gestures, and other modes for communication on both the input and output channel. The elements of a dialogue system are not defined because this idea is under research, however, they are different from chatbot. The typical GUI wizard engages in a sort of dialogue, but it includes very few of the common dialogue system components, and the dialogue state is trivial.
Automatic summarizationAutomatic summarization is the process of shortening a set of data computationally, to create a subset (a summary) that represents the most important or relevant information within the original content. Artificial intelligence algorithms are commonly developed and employed to achieve this, specialized for different types of data. Text summarization is usually implemented by natural language processing methods, designed to locate the most informative sentences in a given document.
Argumentation theoryArgumentation theory, or argumentation, is the interdisciplinary study of how conclusions can be supported or undermined by premises through logical reasoning. With historical origins in logic, dialectic, and rhetoric, argumentation theory includes the arts and sciences of civil debate, dialogue, conversation, and persuasion. It studies rules of inference, logic, and procedural rules in both artificial and real-world settings. Argumentation includes various forms of dialogue such as deliberation and negotiation which are concerned with collaborative decision-making procedures.
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.
Socratic dialogueSocratic dialogue (Σωκρατικὸς λόγος) is a genre of literary prose developed in Greece at the turn of the fourth century BC. The earliest ones are preserved in the works of Plato and Xenophon and all involve Socrates as the protagonist. These dialogues and subsequent ones in the genre present a discussion of moral and philosophical problems between two or more individuals illustrating the application of the Socratic method. The dialogues may be either dramatic or narrative.
Reinforcement learning from human feedbackIn machine learning, reinforcement learning from human feedback (RLHF) or reinforcement learning from human preferences is a technique that trains a "reward model" directly from human feedback and uses the model as a reward function to optimize an agent's policy using reinforcement learning (RL) through an optimization algorithm like Proximal Policy Optimization. The reward model is trained in advance to the policy being optimized to predict if a given output is good (high reward) or bad (low reward).
PersuasionPersuasion or persuasion arts is an umbrella term for influence. Persuasion can influence a person's beliefs, attitudes, intentions, motivations, or behaviours. Persuasion is studied in many disciplines. Rhetoric studies modes of persuasion in speech and writing and is often taught as a classical subject. Psychology looks at persuasion through the lens of individual behaviour and neuroscience studies the brain activity associated with this behaviour. History and political science are interested in the role of propaganda in shaping historical events.
Natural language processingNatural language processing (NLP) is an interdisciplinary subfield of linguistics and computer science. It is primarily concerned with processing natural language datasets, such as text corpora or speech corpora, using either rule-based or probabilistic (i.e. statistical and, most recently, neural network-based) machine learning approaches. The goal is a computer capable of "understanding" the contents of documents, including the contextual nuances of the language within them.
ExperimentAn experiment is a procedure carried out to support or refute a hypothesis, or determine the efficacy or likelihood of something previously untried. Experiments provide insight into cause-and-effect by demonstrating what outcome occurs when a particular factor is manipulated. Experiments vary greatly in goal and scale but always rely on repeatable procedure and logical analysis of the results. There also exist natural experimental studies.
Self-similarityIn mathematics, a self-similar object is exactly or approximately similar to a part of itself (i.e., the whole has the same shape as one or more of the parts). Many objects in the real world, such as coastlines, are statistically self-similar: parts of them show the same statistical properties at many scales. Self-similarity is a typical property of fractals. Scale invariance is an exact form of self-similarity where at any magnification there is a smaller piece of the object that is similar to the whole.
Foundation modelsA foundation model (also called base model) is a large machine learning (ML) model trained on a vast quantity of data at scale (often by self-supervised learning or semi-supervised learning) such that it can be adapted to a wide range of downstream tasks. Foundation models have helped bring about a major transformation in how artificial intelligence (AI) systems are built, such as by powering prominent chatbots and other user-facing AI.
Game mechanicsIn tabletop games and video games, game mechanics are the rules or ludemes that govern and guide the player's actions, as well as the game's response to them. A rule is an instruction on how to play, a ludeme is an element of play like the L-shaped move of the knight in chess. A game's mechanics thus effectively specify how the game will work for the people who play it. There are no accepted definitions of game mechanics.
PlatoPlato (ˈpleɪtoʊ ; Πλάτων ; 428/427 or 424/423 – 348/347 BC) was an ancient Greek philosopher born in Athens during the Classical period in Ancient Greece. In Athens, Plato founded the Academy, a philosophical school where he taught the philosophical doctrines that would later become known as Platonism. Plato (or Platon) was a pen name derived, apparently, from the nickname given to him by his wrestling coach - allegedly a reference to his physical broadness.
Model aircraftA model aircraft is a small unmanned aircraft. Many are replicas of real aircraft. Model aircraft are divided into two basic groups: flying and non-flying. Non-flying models are also termed static, display, or shelf models. Aircraft manufacturers and researchers make wind tunnel models for testing aerodynamic properties, for basic research, or for the development of new designs. Sometimes only part of the aircraft is modelled.
SemEvalSemEval (Semantic Evaluation) is an ongoing series of evaluations of computational semantic analysis systems; it evolved from the Senseval word sense evaluation series. The evaluations are intended to explore the nature of meaning in language. While meaning is intuitive to humans, transferring those intuitions to computational analysis has proved elusive. This series of evaluations is providing a mechanism to characterize in more precise terms exactly what is necessary to compute in meaning.
Similarity (geometry)In Euclidean geometry, two objects are similar if they have the same shape, or if one has the same shape as the mirror image of the other. More precisely, one can be obtained from the other by uniformly scaling (enlarging or reducing), possibly with additional translation, rotation and reflection. This means that either object can be rescaled, repositioned, and reflected, so as to coincide precisely with the other object. If two objects are similar, each is congruent to the result of a particular uniform scaling of the other.
Similarity (philosophy)In philosophy, similarity or resemblance is a relation between objects that constitutes how much these objects are alike. Similarity comes in degrees: e.g. oranges are more similar to apples than to the moon. It is traditionally seen as an internal relation and analyzed in terms of shared properties: two things are similar because they have a property in common. The more properties they share, the more similar they are. They resemble each other exactly if they share all their properties.
Scale modelA scale model is a physical model which is geometrically similar to an object (known as the prototype). Scale models are generally smaller than large prototypes such as vehicles, buildings, or people; but may be larger than small prototypes such as anatomical structures or subatomic particles. Models built to the same scale as the prototype are called mockups. Scale models are used as tools in engineering design and testing, promotion and sales, filmmaking special effects, military strategy, and hobbies such as rail transport modeling, wargaming and racing; and as toys.
