Simplifying Text

"Closed captioning and transcripts are among the tools that have been found to be very useful for alleviating difficulties with reading, spelling, writing, comprehension, and focus."

"Make your information accessible! Having information is important for people with intellectual disabilities. To learn new things. To take part in society. To know their rights and stand up for them. To decide and make their own choices. People with intellectual disabilities have the right to get information that is easy to read and understand."

"... we propose a Multi-Perspective Context Matching (MPCM) model, which is an end-to-end system that directly predicts the answer beginning and ending points in a passage ... Experimental result on the test set of SQuAD shows that our model achieves a competitive result on the leaderboard."

"We’re turning the world’s leading AI research into transformative business applications."

"Teaching machines to read natural language documents remains an elusive challenge. Machine reading systems can be tested on their ability to answer questions posed on the contents of documents that they have seen, but until now large scale training and test datasets have been missing for this type of evaluation. In this work we define a new methodology that resolves this bottleneck and provides large scale supervised reading comprehension data. This allows us to develop a class of […]

"Dr. Will Scott, IBM’s Lead Software Architect on the project, explains further. “Using a cloud-based infrastructure and cognitive computing, Content Clarifier analyzes and condenses content into clearer language, such as by substituting euphemisms with more straightforward verbiage, by adding visuals, or by inserting contextually relevant semantic content (i.e., maps, web resources, phonetic pronunciations). It greatly simplifies the task of reading with the end goal being to increase […]

"The objective of this technique is to ensure that the text of the Web page is not difficult to read. Users with disabilities that make it difficult to decode words and sentences are likely to have trouble reading and understanding complex text. If the text does not require reading ability more advanced than the lower secondary education level, no supplements or alternative versions are needed."

"The best way for AI machines to learn is by feeding them huge data sets of annotated examples, and the Daily Mail has unwittingly created one."

"This study addresses the automatic simplification of texts in Spanish in order to make them more accessible to people with cognitive disabilities. A corpus analysis of original and manually simplified news articles was undertaken in order to identify and quantify relevant operations to be implemented in a text simplification system. The articles were further compared at sentence and text level by means of automatic feature extraction and various machine learning classification algorithms, […]

In this paper, we compare alternative techniques for evaluating a software system for simplifying the readability of texts for adults with mild intellectual disabilities (ID). Using a Wizard-of-Oz prototype, we conducted experiments with a group of adults with ID to test alternative formats of questions to measure comprehension of the information in the news articles. We have found that some forms of questions work well at measuring the difficulty level of a text: multiple-choice questions with […]

"To a very large extent, children learn in and out of school from written text. Information Communications Technologies (ICT) offers many possibilities to facilitate learning by confronting children with multimodal texts. In order to be able to implement learning environments that optimally facilitate children's learning, insight is needed into the cognitive processes underlying text comprehension. In this light, the aim of this special issue is to report on new advances in text […]

"Graph-based notions are increasingly used in biomedical data mining and knowledge discovery tasks. In this paper, we present a clique-clustering method to automatically summarize graphs of semantic predications produced from PubMed citations (titles and abstracts)."

"Over the past two decades, researchers have made great advances in the area of computational methods for extracting meaning from text. This research has to a large extent been spurred by the development of latent semantic analysis (LSA), a method for extracting and representing the meaning of words using statistical computations applied to large corpora of text. Since the advent of LSA, researchers have developed and tested alternative statistical methods designed to detect and analyze […]

Information and Communication Technologies play major role in all types of day to day life activities including Government, public and social domains. The need for HCI aspects to be taken care in these activities has become a predominant one. Especially, incorporating HCI features in the academic environment is getting more attention. In the case of reading materials associated with any type of academic process or content delivery, much focus is to be given so that even people with learning […]

Individuals who access electronic text with Braille and synthetic speech, or who have reading disabilities are often limited in their ability to quickly skim large documents. This paper introduces the use of computer generated text summaries as an alternative method of skimming. Readers with disabilities will more rapidly determine central themes of the material, assess the relevance of a document, identify important segments to be read in detail, or decide to move on to another text. An […]

E-Learning that blends the internet, the web and the educational activities, is becoming one of the prominent ways for defining teaching and learning experiences as anywhere anytime process. Any teaching learning process must be designed to suit the needs of all and must consider all types of learners including people with disabilities. One of the major learning disabilities found related to learners is the problem of reading. Especially for dyslexic reading is a severe problem. In this regard, […]

Book. (Mentions Watson and the Jeopardy challenge.)

"In this paper, we offer set of guidelines and a web service that presents Web texts in a more more accessible way to people with dyslexia. The layout guidelines for developing this service are based on a user study with a group of twenty two dyslexic users. The data collected from our study combines qualitative data from interviews and questionnaires and quantitative data from tests carried out using eye tracking. We analyze and compare both kinds of data and present a set of layout […]

"We present a user study for two different automatic strategies that simplify text content for people with dyslexia. The strategies considered are the standard one (replacing a complex word with the most simpler synonym) and a new one that presents several synonyms for a complex word if the user requests them. We compare texts transformed by both strategies with the original text and to a gold standard manually built. The study was undertook by 96 participants, 47 with dyslexia plus a […]

"...this paper focuses on the design of a summarization tool that provides a summary of reading material which helps the dyslexic to have a first level understanding of the content."

"Easy to Read on the Web” aims at raising awareness and collecting/deriving concise and up-to-date recommendations, guidelines, standards and tools for enhancing the web experience for users with cognitive disabilities and other groups facing problems with “standard” information on the Web." "...this paper discusses the state of the art in Easy to Read on the Web and in related domains and outlines areas of research which should help to better address the needs of people […]

"We systematically examine sixteen features for predicting the difficulty of health texts using six different machine learning algorithms. Three represent new features not previously examined: medical concept density, specificity (calculated using word-level depth in MeSH); and ambiguity (calculated using the number of UMLS Metathesaurus concepts associated with a word). We examine these features for a binary prediction task on 118,000 simple and difficult sentences from a sentence-aligned […]

"My research goal is to advance our understanding of, and quantify, what makes a text easy or difficult to read, in particular for readers with intellectual disabilities."

"The Adaptive Web Browser (AWB) in our design, integrating the technologies of HTML interpreter, text-to-speech engine and picture communication symbols (PCS), facilitates comprehending the contents on web pages with auxiliary speaking sound or picture produced automatically as needed."

"We introduce our research on the development of software to automatically simplify news articles, display them, and read them aloud for adults with ID."

"In this paper we investigate the main linguistic phenomena that can make texts complex and how they could be simplified. We focus on a corpus analysis of simple account texts available on the web for Brazilian Portuguese (BP). This study illustrates the need for text simplification to facilitate accessibility to information by poor readers and by people with cognitive disabilities."

"Pilot study investigated the usability of a simplified e-mail interface designed for people with acquired cognitive-linguistic impairments."

"(1) use pictures, graphics, icons, and symbols to augment text; (2) simplify writing and reading; (3) use consistent navigation and design on every page; (4) use headings, title, and prompts rather than long paragraphs; (5) support screen readers; (6) use larger fonts; (7) use uncluttered, simple screen layout; (8) maintain white space; (9) make the Web site customizable; and (10) use navigation aids."

"The paper presents the results of a user study that investigates the applicability of automatic text modifications to support learning disabled people in text comprehension while browsing the Internet. It presents some results that contradict traditional beliefs in regard to better support reading in this target group by providing them with screen readers."