Textual Segmentation: A Technique for Measuring Comprehension of Lengthy Prose

A simple technique for measuring comprehension of lengthy prose, i.e., consisting of multiple sentences, is presented. The “textual segmentation” procedure requires subjects to partition text into complete, meaningful units, such as paragraphs, chapters, and books. Very easy to prepare, administer, and score, textual segmentation has potentially wide application as a measure of reading comprehension, as a means for studying how people segment prose into paragraphs and the like, as a readability measure, as an instructional tool, and as a criterion for judging the success of text-reading and text-writing computer programs in research on artificial intelligence.

Download Full-text

Evaluation and Comparison of Artificial Intelligence Vision Aids: Orcam MyEye 1 and Seeing AI

Journal of Visual Impairment & Blindness ◽

10.1177/0145482x211027492 ◽

2021 ◽

pp. 0145482X2110274

Author(s):

Christina Granquist ◽

Susan Y. Sun ◽

Sandra R. Montezuma ◽

Tu M. Tran ◽

Rachel Gage ◽

...

Keyword(s):

Artificial Intelligence ◽

Human Performance ◽

Visual Impairments ◽

Light Level ◽

Viewing Distance ◽

Light Perception ◽

Time To Completion ◽

Significant Difference ◽

Text Reading ◽

Size Contrast

Introduction: We compared the print-to-speech properties and human performance characteristics of two artificial intelligence vision aids, Orcam MyEye 1 (a portable device) and Seeing AI (an iPhone and iPad application). Methods: There were seven participants with visual impairments who had no experience with the two reading aids. Four participants had no light perception. Two individuals with measurable acuity and one with light perception were tested while blindfolded. We also tested performance with text of varying appearance in varying viewing conditions. To evaluate human performance, we asked the participants to use the devices to attempt 12 reading tasks similar to activities of daily living. We assessed the ranges of text attributes for which reading was possible, such as print size, contrast, and light level. We also assessed if individuals could complete tasks with the devices and measured accuracy and completion time. Participants also completed a survey concerning the two aids. Results: Both aids achieved greater than 95% accuracy in text recognition for flat, plain word documents and ranged from 13 to 57% accuracy for formatted text on curved surfaces. Both aids could read print sizes as small as 0.8M (20/40 Snellen equivalent, 40 cm viewing distance). Individuals successfully completed 71% and 55% ( p = .114) of tasks while using Orcam MyEye 1 and Seeing AI, respectively. There was no significant difference in time to completion of tasks ( p = .775). Individuals believed both aids would be helpful for daily activities. Discussion: Orcam MyEye 1 and Seeing AI had similar text-reading capability and usability. Both aids were useful to users with severe visual impairments in performing reading tasks. Implications for Practitioners: Selection of a reading device or aid should be based on individual preferences and prior familiarity with the platform, since we found no clear superiority of one solution over the other.

Download Full-text

Differences in Reading Comprehension Text Reading Skills by Using Auditory, Intellectually, Repetition (AIR) and Brainstorming Learning Models in Terms of Students Reading Interest

Proceedings of the 1st Progress in Social Science, Humanities and Education Research Symposium (PSSHERS 2019) ◽

10.2991/assehr.k.200824.011 ◽

2020 ◽

Author(s):

Dia Fitri ◽

Erizal Gani

Keyword(s):

Reading Comprehension ◽

Reading Skills ◽

Learning Models ◽

Text Reading ◽

Reading Interest

Download Full-text

Strategies identification in an experimental reading comprehension task

Zbornik Instituta za pedagoska istrazivanja ◽

10.2298/zipi1002232s ◽

2010 ◽

Vol 42 (2) ◽

pp. 232-246 ◽

Cited By ~ 1

Author(s):

Sanda Stankovic ◽

Dejan Lalovic

Keyword(s):

Reading Comprehension ◽

Multiple Choice Questions ◽

Psychological Practice ◽

Test Taking ◽

Comprehension Task ◽

Comprehension Ability ◽

Test Taking Strategies ◽

Text Reading ◽

Final Score ◽

Ultimate Objective

Standardized reading comprehension tests (RCTs) usually consist of a small number of texts each accompanied by several multiple-choice questions, with texts and questions simultaneously presented. The score the common measure of reading comprehension ability in RCTs is the score. Literature review suggests that strategies subjects employ may influence their performance on RCT, however the score itself provides no information on the specific strategy employed. Knowledge of test-taking strategies could have impact on understanding of the actual purpose and benefits of using RCTs in pedagogical and psychological practice. With the ultimate objective of constructing a first standard RCT in Serbian language, the preliminary step we took was to conduct an experimental reading comprehension task (ERCT) consisting of 27 short texts displayed in succession, each followed by a single multiplechoice question. Using qualitative analysis of subjects? responses in semi-structured postexperimental interview, we identified four overall strategies used on ERCT. Our results show that groups of students who used specific strategies differed significantly from one another in text reading time, with no differences found regarding the question reading and answering time. More importantly, there were no significant between-group differences found in terms of ERCT score. These findings suggest that choice of strategy is a way to optimize the relation between one?s own potential and ERCT task requirements. RCT based on ERCT principles would allow for a flexible choice of strategy which would not influence the final score.

Download Full-text

LEGAL REGULATION OF THE USE OF ARTIFICIAL INTELLIGENCE IN NOTARY AND CIVIL PROCESSES AS AN ELEMENT PROTECTION AND PROTECTION OF THE RIGHTS OF RESIDENTS (RESIDENTS) OF THE TEMPORARILY OCCUPIED TERRITORIES OF UKRAINE

Juridical science ◽

10.32844/2222-5374-2020-103-1.54 ◽

2020 ◽

pp. 447-456

Author(s):

Г. В. Луцька

Keyword(s):

Artificial Intelligence ◽

Social Relations ◽

Computer Programs ◽

Legal Regulation ◽

Civil Procedure ◽

Civil Process ◽

Procedure Code ◽

Occupied Territories ◽

Intelligent Computer ◽

Autonomous Republic

The article considers the problem of application of artificial intelligence in the law of Ukraine in general and in the notarial and civil process in particular. The legal consequences of the legal regime of temporary occupation of some territories of Ukraine are indicated and the ways to eliminate obstacles in the protection and defense of the rights of citizens of Ukraine in these territories are determined. The legal construction of «artificial intelligence» is studied and its types are offered. The conclusion about the expediency of using intelligent computer programs, intelligent information technologies as types of artificial intelligence in notarial and executive processes is substantiated. It is proposed to consider the use of artificial intelligence in notarial and civil proceedings for citizens of Ukraine living in the Autonomous Republic of Crimea or in the occupied territories of Donetsk and Luhansk regions, within the limits, in the manner and in the manner prescribed by law of Ukraine. It is proved that the introduction of artificial intelligence through the mechanism of protection and defense of human and civil rights and freedoms in the civil process must be adapted to social relations that arise and exist, not violate the constitutional rights and freedoms of man and citizen in Ukraine and have a legal basis. Based on the scientific and practical analysis of the Civil Procedure Code of Ukraine, it is proposed for citizens of Ukraine living in the Autonomous Republic of Crimea or in the occupied territories of Donetsk and Luhansk regions to establish that lawsuits, separate and injunctive proceedings are entirely online. The procedure (procedure) and features of such proceedings with the use of various types of artificial intelligence (such as chatbots and other information intelligence technologies) should be defined in the Civil Procedure Code of Ukraine. It is noted that the introduction of the above mechanism to protect and defend the rights of citizens living in the Autonomous Republic of Crimea or in the occupied territories of Donetsk and Luhansk regions through intelligent computer programs will require proper maintenance and support of such programs to prevent leakage of information, leakage of personal data, etc. The conclusion is substantiated that e-litigation and remote notarial proceedings will increase the effectiveness of notarial and judicial forms of protection and protection of rights and make these state forms of protection more flexible, able to anticipate the peculiarities of procedural actions involving residents of the temporarily occupied territories.

Download Full-text

Supplemental Material for What is Text Reading Fluency and Is It a Predictor or an Outcome of Reading Comprehension? A Longitudinal Investigation

Developmental Psychology ◽

10.1037/dev0001167.supp ◽

2021 ◽

Keyword(s):

Reading Comprehension ◽

Reading Fluency ◽

Longitudinal Investigation ◽

Text Reading

Download Full-text

Rethinking Software Protection

Artificial Intelligence and Intellectual Property ◽

10.1093/oso/9780198870944.003.0016 ◽

2021 ◽

pp. 341-362

Author(s):

Peter R Slowinski

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Evolutionary Algorithms ◽

Future Development ◽

Computer Programs ◽

Software Protection ◽

Computing Power ◽

The Core ◽

Quantum Leap ◽

Core Part

The core of artificial intelligence (AI) applications is software of one sort or another. But while available data and computing power are important for the recent quantum leap in AI, there would not be any AI without computer programs or software. Therefore, the rise in importance of AI forces us to take—once again—a closer look at software protection through intellectual property (IP) rights, but it also offers us a chance to rethink this protection, and while perhaps not undoing the mistakes of the past, at least to adapt the protection so as not to increase the dysfunctionality that we have come to see in this area of law in recent decades. To be able to establish the best possible way to protect—or not to protect—the software in AI applications, this chapter starts with a short technical description of what AI is, with readers referred to other chapters in this book for a deeper analysis. It continues by identifying those parts of AI applications that constitute software to which legal software protection regimes may be applicable, before outlining those protection regimes, namely copyright and patents. The core part of the chapter analyses potential issues regarding software protection with respect to AI using specific examples from the fields of evolutionary algorithms and of machine learning. Finally, the chapter draws some conclusions regarding the future development of IP regimes with respect to AI.

Download Full-text