Lexical Surprisal Modeling for Continuous Oral Reading Fluency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing oral reading fluency (ORF) tests require specific, pre-set assessment passages, which disrupt reading for learning and pleasure, and do not account for a reader's familiarity with words, leading to variance in fluency measurements due to passage-specific factors.
Innovation Solution
A system that models a reader's lexical experience using a background corpus, dynamically updating with each word encountered, to generate a surprisal model that adjusts fluency measurements based on familiarity, incorporating text complexity, prosody, and user progress.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pre-set assessment passages are used for ORF testing, then measurement standardization is improved, but passage-specific variance increases and reading for learning and pleasure is disrupted
Solution Approach 1:
The system enables reading materials to serve multiple functions simultaneously - both as assessment passages for ORF testing and as reading material for learning and pleasure. By using dynamically selected passages from the user's actual reading experience rather than pre-set test passages, the system eliminates the need to choose between standardized measurement and reading flexibility, allowing the same text to fulfill both purposes.
2Device complexity
If traditional ORF testing methods are used, then assessment simplicity is maintained, but lexical familiarity effects cause measurement inaccuracy
Solution Approach 1:
The system incorporates feedback loops where the surprisal model continuously updates based on the user's reading progress and lexical encounters. As users read through passages, the system tracks their familiarity with words and adjusts fluency measurements accordingly, allowing repeated words to be scored more leniently and new words more strictly. This dynamic feedback mechanism improves measurement accuracy without significantly increasing system complexity.
Solution Approach 2:
The system dynamically changes the evaluation parameters for fluency assessment based on lexical familiarity. Instead of applying a fixed scoring standard throughout a passage, the system adjusts the tolerance for errors and pauses according to whether a word has been encountered before. This parameter adaptation allows the same assessment system to accurately measure fluency across passages with varying lexical repetition patterns.
3Measurement precision
If dynamic lexical experience modeling is implemented, then fluency measurement accuracy is improved, but computational complexity increases
Solution Approach 1:
The system performs preliminary processing by pre-computing and storing the background corpus and building the surprisal model structure before actual reading assessment begins. By preparing the computational framework in advance - including the language model and lexical tracking structures - the system reduces the computational burden during real-time assessment, making the dynamic modeling feasible without excessive complexity during the actual reading evaluation.
Data Source
AI summary
Systems and methods are provided for modeling lexical experience for tracking of oral reading fluency. In embodiments, a background corpus and a text are received. A reading passage is selected from the text. A surprisal model is generated based on the background corpus and a portion of the text preceding the reading passage. An audio of a user reciting the reading passage is iteratively received, wherein a token of the audio from a plurality of tokens is received at a time. Oral reading fluency is evaluated based on the audio and the surprisal mode. The next reading passage is selected. An oral reading fluency report is stored in a computer readable medium.