Abstract
Semantic similarity measurement can be applied in many different fields and has variety of ways to measure it. As a foundation paper for semantic similarity, we explored the edge counting method for measuring semantic similarity by considering the weighting attributes from where they affect an edge's strength. We considered the attributes of scaling depth effect and semantic relation type extensively. Further, we showed how the existing edge counting method could be improved by considering virtual connection. Finally, we compared the performance of the proposed method with a benchmark set of human judgment of similarity. The results of proposed measure were encouraging compared with other combined approaches.
Original language | English |
---|---|
Pages (from-to) | 470-480 |
Number of pages | 11 |
Journal | Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) |
Volume | 3397 |
DOIs | |
Publication status | Published - 2005 |
Event | 13th International Conference on AIS 2004 - Jeju Island, Korea, Republic of Duration: 2004 Oct 4 → 2004 Oct 6 |
ASJC Scopus subject areas
- Theoretical Computer Science
- General Computer Science