Domain-Specific Vocabulary Spellchecking to Preserve Specialized Terms

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing spellchecking technologies fail to accurately correct domain-specific terms due to the omission of user-provided artifacts from global vocabularies, leading to false negatives and incorrect corrections.

Innovation Solution

Implementing domain-specific vocabularies and regular expressions within a multi-tenant system to prioritize spellchecking against user-specific terms before applying global vocabularies, using NLP annotators to validate corrections and retain meaningful annotations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a global vocabulary is used for spellchecking, then spellchecking coverage is broad, but domain-specific terms are incorrectly corrected

Engineering Contradiction:

Improvespellchecking coverageVSAvoidspellchecking accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The spellchecking system segments the vocabulary into multiple levels: a global vocabulary for general terms and domain-specific vocabularies for specialized terms. The system processes input text by first checking against domain-specific vocabularies, then falling back to the global vocabulary, thereby resolving the contradiction between broad coverage and accurate domain-specific correction.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by making the spellchecking behavior context-dependent. Different vocabularies are applied to different domains or contexts. The system determines which vocabulary to use based on the input text characteristics, ensuring that domain-specific terms are preserved while maintaining general spellchecking capability.

Inventive Principle:

Principle #3Local quality

2Adaptability or versatility

If user-provided artifacts are omitted from global vocabularies, then NLP processing can access custom terms, but spellchecking produces false negatives

Engineering Contradiction:

Improvecustom term accessVSAvoidspellchecking reliability

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent merges the global vocabulary with domain-specific vocabularies into a unified spellchecking system. The combined vocabulary structure allows the system to access both general terms and custom user-provided artifacts simultaneously, eliminating false negatives while maintaining NLP processing capabilities.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system performs preliminary spellchecking against domain-specific vocabularies before falling back to global vocabularies. This preliminary action ensures that custom terms are recognized and corrected before the NLP processing stage, preventing false negatives and improving overall reliability.

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If domain-specific vocabularies are implemented, then spellchecking accuracy improves, but system complexity increases

Engineering Contradiction:

Improvespellchecking accuracyVSAvoidvocabulary management complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements a universal vocabulary management framework that handles multiple vocabularies (global and domain-specific) through a unified processing architecture. The spellchecking system uses a consistent algorithm that automatically selects the appropriate vocabulary level, reducing the operational complexity despite maintaining multiple vocabularies.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS12400076B2Using domain specific vocabularies to spellcheck input strings

Publication Date: 2025.08.26 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Provided are a computer program product, system, and method for using domain specific vocabularies to spellcheck input strings. A determination is made of a determining a domain specific vocabulary comprising domain specific tokens for a user. The input strings in the input text from the user are processed to determine whether the input strings match the domain specific tokens in the domain specific vocabulary. Indication is made that input strings that are determined to match the domain specific tokens in the domain specific vocabulary are not to be spellchecked by a global vocabulary available to users across domains.