Glossary

Word Embeddings

What is Word Embeddings?

Word embeddings represent words as numerical vectors so that words with similar meanings lie close together in vector space, such as “car” and “vehicle”. Methods such as Word2Vec or GloVe learn these vectors from large amounts of text. They were an important step in language processing, for example for search or classification; today's language models use contextual embeddings in which a word is represented differently depending on the sentence.

How KI.ordo helps

KI.ordo's knowledge search does not use embeddings but BM25 keyword search directly on the server.

Topics

NLP
Vectors
Semantics

Try KI.ordo

Agents, flows and templates in one workspace – free 24-hour demo.

Start demo

← All terms

Related terms

Embedding vector

An embedding vector (embedding) is a list of numbers that represents the meaning of a word, sentence or document so that texts with similar content lie close together. This makes it possible to recognise, for example, that 'cancellation' and 'ending the contract' are related even though they share no words. Embeddings underpin many semantic search systems, recommendation services and RAG applications; they are computed by specially trained models.

vector
semantic search
+1

Gensim

Gensim is an open-source Python library for analysing large collections of text. It is known for topic models such as LDA, for training word vectors (for instance Word2Vec, FastText and Doc2Vec) and for comparing documents by similarity. Because Gensim processes data in chunks, it can also handle corpora that do not fit into memory. A typical use: automatically grouping thousands of customer comments by recurring themes.

Python library
Topic modelling
+1

Natural Language Processing (NLP)

Natural language processing is the branch of AI that enables computers to analyse, understand and generate human language in text or speech. It covers tasks such as translation, classification, summarisation, sentiment analysis and question answering. Rules and statistical methods once dominated; today the field is shaped by large language models.

NLP
Language
+1

Semantic analysis

Semantic analysis examines the meaning of language – not just which words appear, but what is meant. This includes interpreting ambiguous words correctly in context (such as “bank” as a financial institution or a riverside), recognising relationships between concepts and classifying statements by content. It underpins applications such as analysing customer feedback, question answering or search systems that should also understand differently worded queries with the same meaning.

NLP
meaning
+1