Quantization

Pruning (Neural)

प्रुनिङ (न्युरल)

Removing unimportant weights or neurons to make a model smaller and faster.

Chunking

चन्किङ / टुक्र्याउने

Splitting long documents into smaller pieces for indexing and retrieval.

Decision Support System

निर्णय सहयोग प्रणाली

Software that analyzes data to help people make better, faster decisions.

Dimensionality Reduction

आयाम न्यूनीकरण

Reducing the number of input features while keeping important information.

Distillation

डिस्टिलेसन

Training a smaller model to mimic a larger one, keeping most of its capability.

Embedding

एम्बेडिङ

A numerical vector that represents the meaning of a word, sentence, or item.

F1 Score

एफ१ स्कोर

A single metric balancing precision and recall into one number.

Lemmatization

लेमाटाइजेसन

Reducing words to their dictionary base form using grammar, e.g. 'better' to 'good'.