NLP Intro
Embedding - answer In the NPL context, an embedding is a technique of representing
words (or other language elements) as a vector, especially when such a representation
is produced by a neural network.
Encoding - answer In an NLP context, the encoding or charter encoding refers to the
mapping from characters, e.g. "a", "?", to bytes.
Knowledge base - answer A knowledge is a collection of knowledge or facts in a
computationally usable format.
Language model - answer In an NLP context, a language model is a model of the
probability distribution of word sequences.
Loss - answer In a machine learning context, loss refers to a measure of how wrong a
supervised model is.
N-gram - answer An N-gram is a subsequence of words. Sometimes. "N-gram" can
refer to a subsequence of characters
Natural language - answer Natural language is a language spoken or signed by people.
In contrast to a programming language which is used for giving instructions to
computers. Natural language also contrasts with artificial or constructed languages,
which are designed by a person or group of people.
Natural language processing (NLP) – answer NLP is a field of computer science and
linguistics focused on techniques and algorithms for processing data, continuing natural
language.
Neural Network - answer An artificial neural network is a collection of neurons
connected by weights.
Parts of speech (POS) - answerPOS are word categories. The most well known are
nouns and verbs. In an NLP context, the Penn Treebank tags are the most frequently
used set of parts of speech.
Regular expression - answerA regular expression is a string that defines a pattern to be
matched in text.
Sentiment - answerIn an NPL context, sentiment is the emotion or option a human
encodes in a language act.
Embedding - answer In the NPL context, an embedding is a technique of representing
words (or other language elements) as a vector, especially when such a representation
is produced by a neural network.
Encoding - answer In an NLP context, the encoding or charter encoding refers to the
mapping from characters, e.g. "a", "?", to bytes.
Knowledge base - answer A knowledge is a collection of knowledge or facts in a
computationally usable format.
Language model - answer In an NLP context, a language model is a model of the
probability distribution of word sequences.
Loss - answer In a machine learning context, loss refers to a measure of how wrong a
supervised model is.
N-gram - answer An N-gram is a subsequence of words. Sometimes. "N-gram" can
refer to a subsequence of characters
Natural language - answer Natural language is a language spoken or signed by people.
In contrast to a programming language which is used for giving instructions to
computers. Natural language also contrasts with artificial or constructed languages,
which are designed by a person or group of people.
Natural language processing (NLP) – answer NLP is a field of computer science and
linguistics focused on techniques and algorithms for processing data, continuing natural
language.
Neural Network - answer An artificial neural network is a collection of neurons
connected by weights.
Parts of speech (POS) - answerPOS are word categories. The most well known are
nouns and verbs. In an NLP context, the Penn Treebank tags are the most frequently
used set of parts of speech.
Regular expression - answerA regular expression is a string that defines a pattern to be
matched in text.
Sentiment - answerIn an NPL context, sentiment is the emotion or option a human
encodes in a language act.
