liveBook · Manning

Multilingual semantic search

As explained in Retrieval Augmented Generation, The Foundational Ideas

Multilingual semantic search retrieves semantically related content across different languages using language-aligned representations.

Multilingual semantic search retrieves related content across languages by placing a sentence and its translation near the same point in embedding space. A bi-encoder can encode documents offline, then encode a query online and search the stored vectors without translating the query. section 2.3.2

Cross-language retrieval

A Spanish query such as “zapatos de correr” can reach English content among 100,000 Quora questions without a translation step. On English-Spanish STS 2017 pairs, the multilingual distilled model scores 83.1 Spearman correlation, versus 54.7 for an English-only fine-tuned model. section 2.3.2

Production design separates representation quality from retrieval cost:

  • Precompute document embeddings and search them in milliseconds at query time. section 2.3.2
  • Do not assume cheap encoding makes comparison cheap: full pairwise similarity remains quadratic, motivating FAISS or batched approximations. section 2.3.2
Listing 2.5 Practical sentence-level similarity with Sentence-BERT.
from sentence_transformers import SentenceTransformer
 
model = SentenceTransformer('all-MiniLM-L6-v2')  #A
 
tickets = [  #B
"My internet connection keeps dropping",
"WiFi connectivity is unstable",
"Billing question about charges"
]
 
ticket_embeddings = model.encode(tickets)  #C
 
query = "Network connection problems"  #D
query_embedding = model.encode([query])
 
similarities = model.similarity(query_embedding, ticket_embeddings)  #E
 
print(f"--- Similarities for query: '{query}' ---")
for i, score in enumerate(similarities[0]):
print(f"Score: {score:.3f} | Ticket: '{tickets[i]}'")
 
 

A compact Sentence-BERT example shows the baseline workflow: encode texts, encode a query, and compare embeddings before extending the setup across languages. section 2.3.2

How Retrieval Augmented Generation, The Foundational Ideas covers it

How deep it goes
Explains teacher-student alignment, offline indexing, online search, evaluation, and quadratic comparison costs.
Examples
Uses Spanish-to-English retrieval, STS 2017 scores, Quora questions, and Sentence-BERT ticket similarity.
What you can do after
Apply it via Sentence-Transformers by encoding multilingual documents and queries, then ranking vector similarities.
How it connects
Connects multilingual alignment with knowledge distillation, sentence embeddings, bi-encoders, vector search, and FAISS.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Retrieval Augmented Generation, The Foundational Ideas. The section links point to the parts of the book it draws on.