Similarity Assessment through blocking and affordance assignment in Textual CBR
This addresses the challenge of improving web page retrieval for users by considering textual affordances, but it appears incremental as it builds on case-based representations and domain-specific testing.
The paper tackles the problem of assessing web page relevance by proposing a method that extracts and assigns affordances to texts, then uses these affordances for retrieval, with promising results tested in the tourism domain.
It has been conceived that children learn new objects through their affordances, that is, the actions that can be taken on them. We suggest that web pages also have affordances defined in terms of the users' information need they meet. An assumption of the proposed approach is that different parts of a text may not be equally important / relevant to a given query. Judgment on the relevance of a web document requires, therefore, a thorough look into its parts, rather than treating it as a monolithic content. We propose a method to extract and assign affordances to texts and then use these affordances to retrieve the corresponding web pages. The overall approach presented in the paper relies on case-based representations that bridge the queries to the affordances of web documents. We tested our method on the tourism domain and the results are promising.