liveBook · Manning

Alternative label

As explained in AI-Powered Search

An alternative label is a domain term or name recognized as an alias for a canonical concept or entity label.

Search users may enter a misspelling, acronym, or valid spelling variant while intending the same domain term. An alternative label maps that variant to a canonical label so the search pipeline can interpret the intended meaning. section 2.4 section 6.5

Alternative labels are replacement term sequences with identical meanings. Initialisms, acronyms, misspellings, and alternative spellings commonly provide them. They form a specific subset of synonym lists, while taxonomies, ontologies, and knowledge graphs add categories, relationships, and entities around the labels. section 2.4

A normalization mapping can represent variants such as:

The usual search behavior is to normalize the less common or incorrect variant into the more common canonical form, then search for that form. Mappings can be stored separately when algorithms generate them and people may review or modify them. Document-based spell-checking and user-interaction signals provide two ways to refine corrections. section 2.4 section 6.5

Figure 2.12 Levels of domain-specific knowledge modeling. Knowledge graphs extend ontologies, which extend taxonomies. Synonyms extend alternative labels and map to entries in taxonomies.
figure

Use the knowledge-modeling diagram to place alternative labels beneath synonym lists and alongside taxonomies, ontologies, and knowledge graphs. section 2.4

How AI-Powered Search covers it

How deep it goes
Defines mappings, gives examples, and names document and signal-based correction approaches without specifying their algorithms.
Examples
Uses RN, CTO, specialise, latop, laptok, and laptop as acronym, spelling-variant, and misspelling examples.
What you can do after
Apply it by mapping variants to canonical labels and searching with the normalized form.
How it connects
Connects alternative labels to synonyms, taxonomies, ontologies, knowledge graphs, misspellings, and query intent.

Related concepts

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