Sowmya Vajjala

Assessing the relative reading level of sentence pairs for text simplification

While the automatic analysis of the readability of texts has a long history, the use of readability assessment for text simplification has received only little attention so far. In this paper, we explore readability models for identifying differences in the reading levels of simplified and unsimplified versions of sentences. Our experiments show that a relative ranking is preferable to an absolute binary one and that the accuracy of identifying relative simplification depends on the initial reading level of the unsimplified version. The approach is particularly successful in classifying the relative reading level of harder sentences. In terms of practical relevance, the approach promises to be useful for identifying particularly relevant targets for simplification and to evaluate simplifications given specific readability constraints.

Exploring Measures of “Readability†for Spoken Language: Analyzing linguistic features of subtitles to identify age-specific TV programs

We investigate whether measures of readability can be used to identify age-specific TV programs. Based on a corpus of BBC TV subtitles, we employ a range of linguistic readability features motivated by Second Language Acquisition and Psycholinguistics research. Our hypothesis that such readability features can successfully distinguish between spoken language targeting different age groups is fully confirmed. The classifiers we trained on the basis of these readability features achieve a classification accuracy of 95.9%. Investigating several feature subsets, we show that the authentic material targeting specific age groups exhibits a broad range of linguistics and psycholinguistic characteristics that are indicative of the complexity of the language used.

Reading demands in secondary school: Does the linguistic complexity of textbooks increase with grade level and the academic orientation of the school track?

An adequate level of linguistic complexity in learning materials is believed to be of crucial importance for learning. The implication for school textbooks is that reading complexity should differ systematically between grade levels and between higher and lower tracks in line with what can be called the systematic complexification assumption. However, research has yet to test this hypothesis with a real-world sample of textbooks. In the present study, we used automatic measures from computational linguistic research to analyze 2,928 texts from geography textbooks from four publishers in Germany in terms of their reading demands. We measured a wide range of lexical, syntactic, morphological, and cohesion-related features and developed text classification models for predicting the grade level (Grades 5 to 10) and school track (academic vs. vocational) of the texts using these features. We also tested ten linguistic features that are considered to be particularly important for a reader’s understanding. The results provided only partial support for systematic complexification. The text classification models showed accuracy rates that were clearly above chance but with considerable room for improvement. Furthermore, there were significant differences across grade levels and school tracks for some of the ten linguistic features. Finally, there were marked differences among publishers. The discussion outlines key components for a systematic research program on the causes and consequences of the lack of systematic complexification in reading materials.

Machine Learning and Applied Linguistics.

This entry introduces the topic of machine learning and provides an overview of its relevance for applied linguistics and language learning. The discussion will focus on giving an introduction to the methods and applications of machine learning in applied linguistics, and will provide references for further study.