Cognitively Motivated Features for Readability Assessment

  title={Cognitively Motivated Features for Readability Assessment},
  author={Lijun Feng and No{\'e}mie Elhadad and Matt Huenerfauth},
We investigate linguistic features that correlate with the readability of texts for adults with intellectual disabilities (ID). Based on a corpus of texts (including some experimentally measured for comprehension by adults with ID), we analyze the significance of novel discourse-level features related to the cognitive factors underlying our users' literacy challenges. We develop and evaluate a tool for automatically rating the readability of texts for these users. Our experiments show that our… 

Tables from this paper

Readability Assessment for Text Simplification

A readability assessment approach to support the process of text simplification for poor literacy readers with a number of new features, and experiment with alternative ways to model this problem using machine learning methods, namely classification, regression and ranking.

A Comparison of Features for Automatic Readability Assessment

It is found that features based on in-domain language models have the highest predictive power and Entity-density and POS-features, in particular nouns, are individually very useful but highly correlated.

Learning Domain-Specific, L1-Specific Measures of Word Readability

This work proposes ways to adapt readability measures for users who (a) are proficient in a particular domain, and (b) have a particular native language (L1) to predict the readability of individual words.

Readability Indices for Automatic Evaluation of Text Simplification Systems: A Feasibility Study for Spanish

This paper adapts three existing readability indices to be computed automatically, which are then applied to a corpus of original news texts and their manual simplifications aimed at people with cognitive disabilities.

Automatic readability assessment for people with intellectual disabilities

This work has used sophisticated computational tools to build an automatic readability metric that exploits global semantic (discourse level) properties of a text, in addition to well-studied lexical and syntactic features.

Are Cohesive Features Relevant for Text Readability Evaluation?

This paper investigates the effectiveness of 65 cohesion-based variables that are commonly used in the literature as predictive features to assess text readability across narrative and informative texts intended for an audience of L2 French learners.

Revisiting the Readability Assessment of Texts in Portuguese

This paper presents experiments to build a readability checker to classify texts in Portuguese, considering different text genres, domains and reader ages, using naturally occurring texts.

Comparing evaluation techniques for text readability software for adults with intellectual disabilities

Alternative techniques for evaluating a software system for simplifying the readability of texts for adults with mild intellectual disabilities (ID) are compared and found that some forms of questions work well at measuring the difficulty level of a text.

Text Readability Assessment for Second Language Learners

A generalization method is applied to adapt models trained on larger native corpora to estimate text readability for learners, and domain adaptation and self-learning techniques are explored to make use of the native data to improve system performance on the limited L2 data.

Measuring text readability with machine comprehension: a pilot study

The hypothesis is that the simpler a text is, the better it should be understood by a machine, and this correlation between readability levels and performance of automatic reading systems is expected to be strong.



Combining Lexical and Grammatical Features to Improve Readability Measures for First and Second Language Texts

This work evaluates a system that uses interpolated predictions of reading difficulty that are based on both vocabulary and grammatical features, and indicates that Grammatical features may play a more important role in second language readability than in first languagereadability.

Generating Readable Texts for Readers with Low Basic Skills

Evaluation with lowskilled readers confirms that SkillSum's knowledge-based microplanning choices enhance readability, and this work discusses future readability improvements.

A machine learning approach to reading level assessment

Syntactic complexity measures for detecting Mild Cognitive Impairment

Different measures of syntactic complexity when extracted from spoken language samples of healthy and cognitively impaired subjects show different patterns for their data set, indicating that using multiple, complementary measures is important for such an application.

On the Failure of Readability Formulas to Define Readable Texts: A Case Study from Adaptations.

IN THE PAST 30 OR 40 YEARS there has been much discussion of objective formulas to measure the readability of texts. These formulas measure variables such as sentence length and familiarity of

Reading Level Assessment Using Support Vector Machines and Statistical Language Models

This paper uses support vector machines to combine features from traditional reading level measures, statistical language models, and other language processing tools to produce a better method of assessing reading level.

A Language Modeling Approach to Predicting Reading Difficulty

A measure based on an extension of multinomial naïve Bayes classification that combines multiple language models to estimate the most likely grade level for a given passage is derived, which is not specific to any particular subject and can be trained with relatively little labeled data.

Derivation of New Readability Formulas (Automated Readability Index, Fog Count and Flesch Reading Ease Formula) for Navy Enlisted Personnel

Three readability formulas were recalculated to be more suitable for Navy use and resulted in a scaled reading grade level based on Navy personnel reading Navy training material and comprehending it.

Sentence Alignment for Monolingual Comparable Corpora

This work addresses the problem of sentence alignment for monolingual corpora by incorporating context into the search for an optimal alignment in two complementary ways: learning rules for matching paragraphs using topic structure and refining the matching through local alignment to find good sentence pairs.

A statistical model for scientific readability

Experiments show that this new method of using statistical models to estimate readability has a better performance than the widely used Flesch-Kincaid readability formula.