We describe a readability assessment approach to support the process of text simplification for poor literacy readers. Given an input text, the goal is to predict its readability level, which corresponds to the literacy level that is expected from the target reader: rudimentary, basic or advanced. We complement features traditionally used for readability assessment with a number of new features, and experiment with alternative ways to model this problem using machine learning methods, namely classification, regression and ranking. The best resulting model is embedded in an authoring tool for Text Simplification.

In today's language-learning classrooms, all of the students in a class almost always have the same text to read. Although students have different reading levels, it is impractical for a single teacher to find unique texts matched to each student's abilities. The REAP system was developed to make the process of providing students with individualized texts practical. The texts come in the form of authentic documents retrieved from the Web, and the system tracks and assesses students ’ knowledge as they use the system. The system is able to find documents that meet various and individualized criteria. In this paper, we describe our work on modeling lexical familiarity. In particular, we detail the approaches taken for modeling the student's vocabulary knowledge, the contents of documents in the corpus, and the components of the curriculum. We also address related and future work. KEY WORDS User modeling and adaptation, computer-based learning, language-learning, and reading-level personalization. 1.

summarisation of discussion fora

Blog posts, news articles and other webpages are present on thewebinmultiplelanguages. Standardsearch enginesevaluate the relevance of the candidate documents to the given query. However, when considering documents with overlapping content, many of them written in a foreign language other than the user’s own native tongue, it is beneficial to promote documents that are easy enough for the user to read. Here, we show how to rank a collection of foreign documents based on both: a) relevance to the query, and b) the comprehension difficulty of the document. We design effective ranking operators that evaluate the difficulty of a foreign document with respect to the user’s native language. We show that existing search engines can easily augment their scoring function by incorporating the proposed comprehensibility metrics. Finally, we provide extensive experimental evidence that the comprehensibility-aware ranking model significantly improves the standard relevance-based ranking paradigm.