Graesser Petschonek 2005 - Automated Systems that Analyze Text and Discourse: QUAID, Coh-Metrix, and AutoTutor

Recent advances in the fields of computational linguistics, discourse processes, and computer technologies offer new avenues of improving measurement methodologies and clinical applications. 

This chapter describes three technologies, available on the web, that have been developed in the interdisciplinary Institute for Intelligent Systems at the University of Memphis. 

QUAID (Question Understanding Aid) critiques questions onsurveys and questionnaires as to whether the questions might pose comprehension difficulties for respondents. 

Coh-Metrix analyzes text on hundreds of metrics of cohesion and language characteristics; it can be used to analyze the readability andcoherence of documents in the health industry. 

AutoTutor is an animated conversational agent that helps individuals learn by holding a conversation in natural language. Although AutoTutor was originally developed as a learning environment for college students, it could be expanded from training to communicating with patients on health problems. 

These new technologies have not yet been assimilated into Quality of Life research and clinical practice so an important next direction is to explore their capabilities.

Enlace al artículo:

http://www.scribd.com/full/45830311?access_key=key-21yufajojat8npsvz14l

Graesser Mcnamara 2009 - Computational analysis of multilevel discourse comprehension

ABSTRACT

The proposed multilevel framework of discourse comprehension includes the surface code, the textbase, the situation model, the genre and rhetorical structure, and the pragmatic communication level.

We describe these five levels when comprehension succeeds and also when there are communication misalignments and comprehension breakdowns. A computer tool has been developed, called Coh-Metrix, that scales discourse (oral or print) on dozens of measures associated with the first four discourse levels. The measurement of these levels with an automated tool helps researchers track and better understand multilevel discourse comprehension.

Two sets of analyses illustrate the utility of Coh-Metrix in discourse theory and educational practice. First, Coh-Metrix was used to measure the cohesion of the text base and situation model, as well as potential extraneous variables, in a sample of published studies that manipulated text cohesion. This analysis helped us better understand what was precisely manipulated in these studies and the implications for discourse comprehension mechanisms. Second, Coh-Metrix analyses are reported for samples of narrative and science texts in order to advance the argument that traditional text difficulty measures are limited because they fail to accommodate most of the levels of the multilevel discourse comprehension framework.

ARTÍCULO:
http://www.scribd.com/full/45830296?access_key=key-23o2acpt1tyi1jf3obls

Comprensión del discurso escrito

1. Psicolingüística y comprensión

2. Lengua oral y lengua escrita

3. Modelos de comprensión del discurso:
Kintsch y van Dijk 1978
van Dijk y Kintsch 1983

4. Inferencias: Concepto

5. Inferencias: Clasificaciones

6. Modelo de Construcción-Integración
Kintsch 1988, 1998

7. Estrategias de comprensión: concepto y clasificaciones

8. Modelo de Indexación de Eventos

9. Corporeidad y comprensión del discurso: Experimentador Inmerso

10. Modelo de comprensión Gómez Macker y Peronard

11. Aprender a partir del texto: Kintsch y McNamara

12. Aprender a partir del texto: Goldman y ELV

13: Metacognición y metacomprensión