Question answeringQuestion answering (QA) is a computer science discipline within the fields of information retrieval and natural language processing (NLP) that is concerned with building systems that automatically answer questions that are posed by humans in a natural language. A question-answering implementation, usually a computer program, may construct its answers by querying a structured database of knowledge or information, usually a knowledge base. More commonly, question-answering systems can pull answers from an unstructured collection of natural language documents.
Two-streams hypothesisThe two-streams hypothesis is a model of the neural processing of vision as well as hearing. The hypothesis, given its initial characterisation in a paper by David Milner and Melvyn A. Goodale in 1992, argues that humans possess two distinct visual systems. Recently there seems to be evidence of two distinct auditory systems as well. As visual information exits the occipital lobe, and as sound leaves the phonological network, it follows two main pathways, or "streams".
Formal semantics (natural language)Formal semantics is the study of grammatical meaning in natural languages using formal tools from logic, mathematics and theoretical computer science. It is an interdisciplinary field, sometimes regarded as a subfield of both linguistics and philosophy of language. It provides accounts of what linguistic expressions mean and how their meanings are composed from the meanings of their parts. The enterprise of formal semantics can be thought of as that of reverse-engineering the semantic components of natural languages' grammars.
Yes–no questionIn linguistics, a yes–no question, also known as a binary question, a polar question, or a general question, is a question whose expected answer is one of two choices, one that provides an affirmative answer to the question versus one that provides a negative answer to the question. Typically, in English, the choices are either "yes" or "no". Yes–no questions present an exclusive disjunction, namely a pair of alternatives of which only one is a felicitous answer.
Word embeddingIn natural language processing (NLP), a word embedding is a representation of a word. The embedding is used in text analysis. Typically, the representation is a real-valued vector that encodes the meaning of the word in such a way that words that are closer in the vector space are expected to be similar in meaning. Word embeddings can be obtained using language modeling and feature learning techniques, where words or phrases from the vocabulary are mapped to vectors of real numbers.
Night visionNight vision is the ability to see in low-light conditions, either naturally with scotopic vision or through a night-vision device. Night vision requires both sufficient spectral range and sufficient intensity range. Humans have poor night vision compared to many animals such as cats, foxes and rabbits, in part because the human eye lacks a tapetum lucidum, tissue behind the retina that reflects light back through the retina thus increasing the light available to the photoreceptors.
Peripheral visionPeripheral vision, or indirect vision, is vision as it occurs outside the point of fixation, i.e. away from the center of gaze or, when viewed at large angles, in (or out of) the "corner of one's eye". The vast majority of the area in the visual field is included in the notion of peripheral vision. "Far peripheral" vision refers to the area at the edges of the visual field, "mid-peripheral" vision refers to medium eccentricities, and "near-peripheral", sometimes referred to as "para-central" vision, exists adjacent to the center of gaze.
Sentence embeddingIn natural language processing, a sentence embedding refers to a numeric representation of a sentence in the form of a vector of real numbers which encodes meaningful semantic information. State of the art embeddings are based on the learned hidden layer representation of dedicated sentence transformer models. BERT pioneered an approach involving the use of a dedicated [CLS] token preprended to the beginning of each sentence inputted into the model; the final hidden state vector of this token encodes information about the sentence and can be fine-tuned for use in sentence classification tasks.
Generative modelIn statistical classification, two main approaches are called the generative approach and the discriminative approach. These compute classifiers by different approaches, differing in the degree of statistical modelling. Terminology is inconsistent, but three major types can be distinguished, following : A generative model is a statistical model of the joint probability distribution on given observable variable X and target variable Y; A discriminative model is a model of the conditional probability of the target Y, given an observation x; and Classifiers computed without using a probability model are also referred to loosely as "discriminative".
Night-vision deviceA night-vision device (NVD), also known as a night optical/observation device (NOD), night-vision goggle (NVG), is an optoelectronic device that allows visualization of images in low levels of light, improving the user's night vision. The device enhances ambient visible light and converts near-infrared light into visible light which can be seen by the user; this is known as I2 (). By comparison, viewing of infrared thermal radiation is referred to as thermal imaging and operates in a different section of the infrared spectrum.
