Automatically generating reading lists
نویسنده
چکیده
| 3
منابع مشابه
Structured Generation of Technical Reading Lists
Learners need to find suitable documents to read and prioritize them in an appropriate order. We present a method of automatically generating reading lists, selecting documents based on their pedagogical value to the learner and ordering them using the structure of concepts in the domain. Resulting reading lists related to computational linguistics were evaluated by advanced learners and judged...
متن کاملAutomatically Generating and Validating Reading-Check Questions
We describe a method used in the REAP tutor to automatically check whether students are reading practice texts for English vocabulary learning. The number of texts used by the REAP tutor and challenges of automatically generating reading comprehension questions necessitated a simpler type of question that could be computer-generated. We describe an algorithm for generating such reading-check qu...
متن کاملDesign controversies and the generation effect: support for an item-order hypothesis.
We performed three experiments to investigate an earlier finding of Nairne, Riegler, and Serra (1991) that item generation disrupts the long-term retention of serial order. Experiment 1 demonstrated a clear advantage of reading over generating on a reconstruction test when reading and generating occurred in pure, but not mixed, lists. Experiment 2 showed that the standard generate advantage is ...
متن کاملGenerating Questions Automatically from Informational Text
Good readers ask themselves questions during reading. Our goal is to scaffold this self-questioning strategy automatically to help children in grades 1-3 understand informational text. In previous work, we showed that instruction for self-questioning can be generated for narrative text. This paper tests the generality of that approach by applying it to informational text. We describe the modifi...
متن کاملLessons Learned in Automatically Detecting Lists in OCRed Historical Documents
Lists are often the most data-rich parts of a document collection, but are usually not set apart explicitly from the rest of the text, especially in a corpus of historical OCRed documents. There are many kinds of lists, differing from each other in both layout and content. Writing individualized code to process all possible types of lists is an expensive challenge. In the present research, we f...
متن کامل