Week 1 Flashcards
What is Natural Language Processing (NLP)?
NLP is the field that focuses on the interaction between computers and human language, aiming to program computers to process and analyse large amounts of natural language data.
What are the two primary types of language data in NLP?
Text and Speech/Audio.
Name three core applications of NLP.
Machine Translation, Chatbots & Dialogue Systems, and Text Summarization.
What is the role of linguistics in NLP?
Linguistics provides insights on language structure and meaning, which help in designing algorithms that can process language accurately.
What is Orthography in NLP?
Orthography refers to the conventions of writing in a language, including spelling and punctuation.
Define Phonology.
Phonology is the study of sound organization within languages, including pronunciation and intonation.
What is Morphology?
Morphology studies the structure of words and how they are formed using roots, prefixes, and suffixes.
Explain Syntax.
Syntax is the set of rules that dictates sentence structure, organizing words into phrases and sentences.
What is the difference between Semantics and Pragmatics?
Semantics is the study of meaning in language, while Pragmatics focuses on meaning in context, considering how words are used in real situations.
Why is Tokenization important in NLP?
Tokenization divides text into individual elements (tokens), which simplifies processing and analysis.
What is Named Entity Recognition (NER)
NER identifies real-world entities, like names, locations, or organizations, within text.
What is the purpose of Language Models (LMs) in NLP?
Language models predict text sequences, helping in tasks like text generation and machine translation.
What are Rule-Based Algorithms in NLP?
These are algorithms that follow predefined human rules to process and analyse language.
Describe Supervised Learning in NLP.
Supervised Learning is a machine learning approach where models are trained on labelled data to make predictions (e.g., classifying spam emails).
What is Unsupervised Learning in NLP?
Unsupervised Learning identifies patterns in data without labels, such as clustering similar topics in documents.