Skip to content
Category

Natural Language Processing

93 terms in the Natural Language Processing domain — each bilingual TR/EN with related-term graph.

Text PreprocessingTokenizationEmbeddingsLanguage ModelingText ClassificationSentiment AnalysisNamed Entity RecognitionInformation ExtractionText SummarizationQuestion AnsweringMachine TranslationSemantic Similarity

Most Read

All Terms (93)

S
17 terms

Semantic Caching

A system approach that reduces latency and cost by reusing prior answers for semantically identical or similar queries.

🤝

Semantic Textual Similarity

A task that measures how semantically close two texts are regardless of surface-level overlap.

📍

Sentence Boundary Detection

The task of reliably identifying sentence starts and boundaries in text.

🧾

Sentence Embeddings

An embedding approach focused on producing semantic representations at the sentence or short-text level.

🧱

SentencePiece

A tokenization framework that can learn subword vocabularies from raw text without relying on whitespace segmentation.

😊

Sentiment Analysis

An NLP task focused on determining the positive, negative, or neutral emotional orientation of a text.

🧾

Slot Filling

An information extraction approach focused on automatically filling predefined information fields from text.

🗂️

Sparse Neural Embeddings

A representation approach that uses neural models to produce semantic signals while preserving sparse-retrieval-style interpretability.

🗂️

Sparse Retrieval

A classical yet still powerful retrieval approach based on term- or word-level matching.

✍️

Spelling Correction

A preprocessing technique that converts misspelled text into more accurate forms to improve downstream NLP quality.

🧭

Stance Detection

A task focused on identifying a text’s stance toward a given claim, topic, or target.

🌱

Stemming

An approach that reduces a word to a shorter root-like form by crudely stripping suffixes.

🚫

Stopword Filtering

A classical preprocessing technique based on removing frequent words that are assumed to have low semantic contribution.

🧾

Structured Output Prompting

A technique that asks the model to produce schema-aligned outputs such as JSON or tables instead of free text.

🧩

Subword Tokenization

An approach that splits rare words into smaller meaningful pieces to balance vocabulary size and coverage.

🧭

Summary Faithfulness

A quality dimension describing how faithfully a generated summary remains grounded in the source text.

🎯

Supervised Fine-Tuning

The process of steering a pretrained model toward more specific behavior using labeled task data.