NLP Concepts
The core tasks of language processing.
This is an overview — pick a sub-topic below.
Sub-topics (12)
Text Preprocessing and Tokenization
Clean text and split it into tokens (words or sub-words) a model can process.
Stemming and Lemmatization
Reduce words to a base form: stemming chops suffixes, lemmatization uses a dictionary.
Part-of-Speech Tagging and Named Entity Recognition
Label words as nouns/verbs, and find names of people, places, organisations and dates.
Text Classification and Sentiment Analysis
Assign categories or sentiment (positive/negative) to text.
Topic Modeling and Keyword Extraction
Discover themes in many documents and extract key phrases.
Summarization, Translation and Question Answering
Generate summaries, translate between languages, and answer questions from text.
Semantic Search, Embeddings and Vector Search
Represent text as vectors so similar meanings are close; search by meaning, not keywords.
Information Retrieval and Extraction
Find relevant documents (retrieval) and pull structured facts from them (extraction).
Spell Checking and Grammar Correction
Detect and fix spelling and grammar mistakes.
Text Generation and Conversational AI
Generate text and hold dialogues — chatbots and assistants.
Knowledge Graphs
Store facts as entities and relationships for reasoning and search.
Speech-to-Text and Text-to-Speech
Convert between spoken audio and text.
Spotted a mistake or want to add detail? Suggest an improvement — Content Contributors' edits are reviewed by editors before they go live.
Discussion (0)
Sign in or join free to ask questions and discuss this topic.