Flashcard: AI Language Interaction and Technologies — 10 carte

NLP — core task?

Extract meaning from human language

NLP — definition?

Enables machines to interpret and generate human language.

Classical NLP pipeline — step?

Tokenization, morphology, syntax, semantics, pragmatics

Transformers — key feature?

Parallel processing with self-attention mechanisms.

Word embeddings — type?

Vector representations capturing similarity

Large Language Models — examples?

BERT, GPT, T5.

Static embeddings — limitation?

Limited polysemy handling, fixed meaning.

Tokenization — role?

Splits text into words or subword units.

Syntax parsing — purpose?

Builds sentence structure trees or dependencies.

Responsible NLP — concerns?

Bias, fairness, privacy, energy use.