1 / 1

Evaluating an Authoring Tool for Mini-Dialogs

Evaluating an Authoring Tool for Mini-Dialogs. Mini-Dialogs A widely used form of Instructional Content in Alelo’s Tactical Language and Culture Learning Systems (TLCTS) About 800 in Tactical Iraqi and Over 300 in Tactical French About 15% of all instructional content. Authoring Mini-Dialogs

trung
Télécharger la présentation

Evaluating an Authoring Tool for Mini-Dialogs

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Evaluating anAuthoring Tool for Mini-Dialogs Mini-Dialogs A widely used form of Instructional Content in Alelo’s Tactical Language and Culture Learning Systems (TLCTS) About 800 in Tactical Iraqi and Over 300 in Tactical French About 15% of all instructional content Authoring Mini-Dialogs Involves manual authoring of large number of Answer / Feedback pairs Utterance Templates Tiny Generative Grammars can be used to create many variation of answers associated with similar feedback Example:$chunk1 = (va commencer |commencera );$chunk2 = (par |avec ); $chunk3 = (les |des );$answer = On $chunk1 $chunk2 $chunk3 armes individuelles.;Generates 8 variations of an answer New Authoring Tools: Templatizer For example-driven utterance template creation Uses Power Operations (Optionalize, Replace, Move) To make underlying grammar concepts easier to use by Non Computational Linguists Evaluation Four subjects Content Developers Three Tasks (1 hour long)Split into Four Edit Sessions Outcome Metrics: Authored content qualityNumber of useful answers Subjective Questionnaire Observations More edits lead to better coverage of answers at the cost of precision (some unwanted answers) Templatizer used more often during First Edit Mostly positive feedback on Questionnaire Rohit Kumar, Alicia Sagae, Lewis JohnsonLook for our other paper in the (Scalability Issues in AIED) Workshop

More Related