Semantic snippet construction for search engine results based on segment evaluation
This addresses the challenge of improving user click-through rates in search engines by providing more relevant snippets, though it appears incremental compared to existing snippet generation methods.
The paper tackles the problem of constructing search engine result snippets by proposing a semantic evaluation approach that identifies target segments in web pages based on multiple factors, with a prototype implementation confirming empirical validation.
The result listing from search engines includes a link and a snippet from the web page for each result item. The snippet in the result listing plays a vital role in assisting the user to click on it. This paper proposes a novel approach to construct the snippets based on a semantic evaluation of the segments in the page. The target segment(s) is/are identified by applying a model to evaluate segments present in the page and selecting the segments with top scores. The proposed model makes the user judgment to click on a result item easier since the snippet is constructed semantically after a critical evaluation based on multiple factors. A prototype implementation of the proposed model confirms the empirical validation.