CSCI372

Which process involves breaking text into individual words or phrases?

• Normalization

• Tokenization

• Text sectioning

• Document triage

What is the purpose of UTF-8 encoding?

• To represent text in binary format

• To identify the language of a text

• To perform sentiment analysis

• To handle characters from various languages

Which of the following is an application of Natural Language Processing (NLP)?

• Image recognition

• Speech synthesis

• Weather forecasting

• Data preprocessing

Which process involves identifying the structure of a sentence?

• Syntactic parsing

• Semantic parsing

• Lexical analysis

• Morphological analysis

Finite state automata/transducers are commonly used for:

• Syntactic parsing

• Semantic analysis

• Text classification

• Lexical analysis

What is the first step in text pre-processing?

• Document triage

• Tokenization

• Text segmentation

• Semantic analysis

Natural language understanding is concerned with:

• Generating human-like text

• Understanding the meaning of text

• Converting images into text

• Translating text from one language to another

What is the difference between morphology and phonology?

• Morphology deals with the structure of words, while phonology deals with the structure of sentences.

• Morphology deals with the structure of sentences, while phonology deals with the structure of words.

• Morphology focuses on sounds in language, while phonology focuses on word formation.

• Morphology analyzes word forms, while phonology analyzes the sound patterns of language.

What is the stem of the verb "ran"?

What is the root of the verb "ran"?