Paper: Rule-based and machine learning approaches for second language sentence-level readability

ACL ID W14-1821
Title Rule-based and machine learning approaches for second language sentence-level readability
Venue Innovative Use of NLP for Building Educational Applications
Session
Year 2014
Authors

We present approaches for the identifica- tion of sentences understandable by sec- ond language learners of Swedish, which can be used in automatically generated ex- ercises based on corpora. In this work we merged methods and knowledge from ma- chine learning-based readability research, from rule-based studies of Good Dictio- nary Examples and from second language learning syllabuses. The proposed selec- tion methods have also been implemented as a module in a free web-based lan- guage learning platform. Users can use different parameters and linguistic filters to personalize their sentence search with or without a machine learning component assessing readability. The sentences se- lected have already found practical use as multiple-choice exercise items within the same platform. Out of a...