Recommending Learning Resources with Selected Passage based on Latent Topics in E-Text


Abstract: When readers have difficulty to understand any part of the e-text, they may want to find some learning resources to help them understand. Treating the whole unclear passage as the query and submit it to a search engine is unsuccessful since existing search engines were designed to accept small queries. In addition, as search engines usually transform the query and candidate resources into bags or vectors of words, the semantic topics underlying the content are totally overlooked. We believe that topics offer a better choice for truly understanding both the query and the candidate documents. In this paper, we propose a novel system for e-texts that facilitates the learning process by enabling search using as queries text passages of any length and retrieving a ranked list of resources (documents, videos, etc) that match the different topics covered within the selected passage. Our early experimental results show that the proposed approach is promising and effective.

4 pages

  • External Posting Date: February 21, 2014 [Abstract]. Approved for External Publication - External Copyright Consideration
  • Internal Posting Date: February 21, 2014 [Fulltext]

Back to Listing