Synonym Identification Using Edit Distance and Knowledge Base
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search technologies fail to accurately identify Chinese synonyms, leading to unreliable search results and user dissatisfaction, as they rely on arbitrary page rank scores and lack effective validation of semantic similarity.
Innovation Solution
A method and apparatus that utilize the shortest edit distance algorithm and a knowledge database to determine Chinese synonyms by comparing words' edit distances, segmenting unfound words, and validating their semantics through a knowledge database and common character table, ensuring accurate synonym identification and minimal expression variance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If page rank score is used to determine synonym relationship, then automatic identification can be performed, but the reliability of synonym identification deteriorates due to arbitrary and uncontrollable resources
Solution Approach 1:
The patent changes the parameter for measuring semantic similarity from arbitrary page rank scores to edit distance, which quantifies the minimum number of operations needed to transform one word into another. This parameter change enables reliable automatic synonym identification by using a controlled, measurable metric that reflects actual linguistic relationships rather than arbitrary resource-based scores.
2Measurement precision
If synonym replacement is applied to search results, then search accuracy improves, but user experience deteriorates when users see unexpected term replacements
Solution Approach 1:
The patent applies local quality by differentiating between exact matches and synonym replacements in search results. Exact matches are highlighted to maintain user familiarity and comfort, while synonym replacements are applied transparently to enrich results without surprising users. This localized differentiation ensures that search accuracy improves through synonym inclusion while user experience is preserved through predictable result presentation.
Data Source
AI summary
A method and an apparatus for identifying synonym and utilizing such synonym to conduct search is disclosed. The disclosed method includes: obtaining arbitrary two words to be identified; determining whether a shortest edit distance between the two words less than or equal to an edit distance threshold; determining whether the two words to be identified exist in a preset knowledge database, and if an answer is yes then searching a smallest granularity type with highest weight value for each word in the knowledge database; and if the two word have the same smallest granularity type with highest weight value, then determining such two words are synonyms, or non-synonym otherwise. The disclosed techniques greatly improve accuracy of synonym identification and guarantee effect of synonym identification.