| 1. |
- Falkenjack, Johan, 1986-, et al.
(author)
-
Classifying easy-to-read texts without parsing
- 2014
-
In: Proceedings of the 3rd Workshop on Predicting and Improving Text Readability for Target Reader Populations (PITR). - : Association for Computational Linguistics. - 9781937284916 ; , s. 114-122
-
Conference paper (peer-reviewed)abstract
- Document classification using automated linguistic analysis and machine learning (ML) has been shown to be a viable road forward for readability assessment. The best models can be trained to decide if a text is easy to read or not with very high accuracy, e.g. a model using 117 parameters from shallow, lexical, morphological and syntactic analyses achieves 98,9% accuracy. In this paper we compare models created by parameter optimization over subsets of that total model to find out to which extent different high-performing models tend to consist of the same parameters and if it is possible to find models that only use features not requiring parsing. We used a genetic algorithm to systematically optimize parameter sets of fixed sizes using accuracy of a Support Vector Machine classi- fier as fitness function. Our results show that it is possible to find models almost as good as the currently best models while omitting parsing based features.
|
|
| 2. |
- Heimann Mühlenbock, Katarina, 1952, et al.
(author)
-
Studies on automatic assessment of students' reading ability
- 2014
-
In: Proceedings of the Fifth Swedish Language Technology Conference. SLTC 2014..
-
Conference paper (peer-reviewed)abstract
- We report results from ongoing research on developing sophisticated measures for assessing a student's reading ability and a tool for the student and teacher to create a profile of this ability. In the project we will also investigate how these measures can be transformed to values on known criteria like vocabulary, grammatical fluency and so forth, and how these can be used to analyse texts. Such text criteria, sensitive to content, readability and genre in combination with the profile of a student's reading ability will form the base to individually adapted texts. Techniques and tools will be developed for selecting suitable texts, automatic summarisation of texts and automatic transformation to easy-to-read Swedish.
|
|
