Term Set Expansion via Semantic Similarity Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual categorization of products on shopping sites is inefficient and burdensome, especially when new products are introduced frequently, leading to delays in registering categories for new products.
Innovation Solution
A set expansion processing device that automatically selects candidates for terms belonging to the same category semantically by receiving a seed string, searching documents, segmenting text, computing scores based on variance and distance, and selecting suitable segment components as instance candidates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual categorization is used to register product categories, then category assignment accuracy can be maintained, but the productivity deteriorates when new products are introduced frequently
Solution Approach 1:
The system performs automatic category candidate selection using computational algorithms that analyze product information and retrieve relevant category terms from external resources, enabling the system to serve itself without manual intervention for category assignment
Solution Approach 2:
The manual mechanical process of category assignment is replaced by an automated information processing system that uses computational algorithms, external resource retrieval, and scoring mechanisms to select category candidates automatically
2Productivity
If automatic category selection algorithms are used, then productivity is improved, but the measurement precision deteriorates due to inaccurate category assignment
Solution Approach 1:
External resources such as Wikipedia and other lexical databases are introduced as intermediaries to provide authoritative category term definitions and relationships, improving the accuracy of automatic category selection
Solution Approach 2:
The category selection process is divided into distinct segments: product information analysis, external resource retrieval, candidate selection, and scoring, allowing each segment to be optimized independently for accuracy
3Measurement precision
If extensive external resources are retrieved and analyzed, then the measurement precision is improved, but the use of energy and processing time increases
Solution Approach 1:
The system retrieves and analyzes only the necessary portion of external resources required for accurate category selection, avoiding unnecessary processing of excessive data while maintaining selection precision
Solution Approach 2:
The system dynamically adjusts processing parameters such as the number of external resources retrieved and the depth of analysis based on product characteristics and category complexity, optimizing computational resource usage
Data Source
AI summary
A receiving unit (101) receives a seed string. A search unit (102) searches snippets of documents containing the seed string. A segment acquisition unit (103) obtains segments by partitioning the snippets using a segment partition string. A segment component acquisition unit (104) obtains segment components by partitioning the segments using a segment component partition string. A segment score computation unit (105) calculates a segment score for a segment based on the standard deviation of the lengths of the segment components. A segment component score computation unit (106) calculates a segment component score for a segment component based on the segment score and the distance between the position of the seed string and the position of the segment component. A selection unit (107) selects any of the segment components as candidates for instances contained in the expanded set of the seed string based on the segment component scores.