Semantic similarity

As explained in Effective Conversational AI

Semantic similarity is the degree of shared meaning between two pieces of text, typically estimated from their representations.

Semantic similarity estimates how closely two texts match in meaning. In retrieval-augmented generation (RAG), it helps find relevant passages even when a question and passage do not use the same words. section 6.3.2

From question to relevant passage

A chatbot question is converted into a vector using the same embedding model as the indexed document chunks. The vector database searches for passages with similar meaning, which are passed to the language model to generate a response. section 6.3.2

Figure 6.9 RAG uses a vector database during build time and run time.

See how vector-database retrieval supports RAG during preparation and at runtime. section 6.3.2

How Effective Conversational AI covers it

How deep it goes

Explains vector-space matching and runtime retrieval, but does not specify a similarity formula or threshold.

Examples

Uses indexed document chunks and user questions, then compares generated answers with expected responses.

What you can do after

Evaluate response relevance by scoring semantic similarity and informativeness, comparing generated and expected answers, and reviewing precision, recall, and F1.

How it connects

Connects embeddings and vector databases to retrieval-augmented generation (RAG).

liveBookmanning.com

Read Effective Conversational AI on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  AI-Powered SearchSemantic textual similarity is the task or measure of determining how closely two text segments correspond in meaning.
• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionSemantic similarity is the degree to which two language items have similar meanings or contextual associations.
• 

  liveBookmanning.com
  Math and Architectures of Deep LearningSimilarity of meaning between terms or documents, as opposed to exact string overlap.
• 

  liveBookmanning.com
  Building Reliable AI SystemsA measure of how closely the meanings of two pieces of content correspond.

Compare how 5 books explain semantic similarity →

Related concepts

• BERTScoremeasured by · BERTScore is an automatic text-generation evaluation metric that compares candidate and reference texts using contextual representations of their tokens.
• similarity searchused by · Similarity search is a retrieval technique that finds or ranks items by comparing their representations with a query according to a similarity or distance measure.
• embeddingmeasures · A numerical vector representation of an item or input that encodes features or relationships useful for computational tasks.

This explainer was generated by Manning's knowledge graph from the text of Effective Conversational AI. The section links point to the parts of the book it draws on.