Student achievement and French sentence repetition test scores

LREC 2014  ·  Deryle Lonsdale, Benjamin Millard ·

Sentence repetition (SR) tests are one way of probing a language learner{'}s oral proficiency. Test-takers listen to a set of carefully engineered sentences of varying complexity one-by-one, and then try to repeat them back as exactly as possible. In this paper we explore how well an SR test that we have developed for French corresponds with the test-taker{'}s achievement levels, represented by proficiency interview scores and by college class enrollment. We describe how we developed our SR test items using various language resources, and present pertinent facts about the test administration. The responses were scored by humans and also by a specially designed automatic speech recognition (ASR) engine; we sketch both scoring approaches. Results are evaluated in several ways: correlations between human and ASR scores, item response analysis to quantify the relative difficulty of the items, and criterion-referenced analysis setting thresholds of consistency across proficiency levels. We discuss several observations and conclusions prompted by the analyses, and suggestions for future work.

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here