Ambiguous Term Annotation via Contextual Distance Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to accurately annotate ambiguous terms in electronic text documents using controlled vocabularies, as they often fail to discern the intended meaning within the context of the document, leading to incorrect annotations.
Innovation Solution
A method that determines ambiguous terms by searching for incongruous term pairs in a controlled vocabulary and annotates them only if specific semantic context terms are present within a predetermined textual distance in the document, ensuring accurate meaning assignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automatic annotation of ambiguous terms is performed using controlled vocabulary, then productivity is improved, but measurement precision deteriorates due to incorrect meaning assignment
Solution Approach 1:
The patent introduces an intermediary disambiguation process that mediates between the automatic annotation system and the controlled vocabulary. This intermediary analyzes contextual terms surrounding the ambiguous term and selects the appropriate meaning from multiple candidates, ensuring accurate meaning assignment while maintaining automated annotation efficiency.
Solution Approach 2:
The system implements feedback mechanisms where the contextual analysis results are used to refine and adjust the meaning selection. The annotation process incorporates feedback from surrounding terms to verify and correct meaning assignments, improving precision while maintaining productivity through automated iterative refinement.
2Measurement precision
If contextual analysis is performed to determine proper meaning, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent segments the contextual analysis process into distinct modular components: identifying ambiguous terms, extracting contextual terms within a specified radius, selecting relevant context, and matching with controlled vocabulary meanings. This segmentation reduces system complexity by making each component independent and manageable while maintaining high measurement precision through coordinated operation of segments.
Solution Approach 2:
The system applies local quality by focusing contextual analysis only on terms within a specific radius around the ambiguous term, rather than analyzing the entire document. This localized approach improves measurement precision for the target term while reducing overall device complexity by limiting the scope of analysis to relevant local contexts.
3Measurement precision
If multiple contextual terms are considered within a predetermined radius, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The patent applies partial action by considering only a predetermined number of contextual terms within a specified radius around the ambiguous term, rather than analyzing all possible context. This partial analysis achieves sufficient disambiguation accuracy for most cases while significantly reducing the time required compared to comprehensive contextual analysis.
Data Source
AI summary
Computer-program products and methods for automatically annotating terms, such as ambiguous terms, in an electronic text document are disclosed. In one embodiment, a method of annotating a text document includes determining, by a computing device, a term of interest within the text document. The method further includes searching a data structure including incongruous term pairs (tx, tt) determined from a controlled vocabulary for the term of interest appearing as a term tt, wherein the term tt is a linguistic head of a term tx of the incongruous term pairs (tx, tt). The method further includes annotating the term of interest with a meaning provided by the controlled vocabulary only if a term tx of the incongruous term pairs (tx, tt) associated with the term of interest in the data structure is not present within a predetermined textual distance of the term of interest in the text document.