Adel Elsayed

A Corpus-based Evaluation of a Domain-specific Text to Knowledge Mapping Prototype

The aim of this paper is to evaluate a Text to Knowledge Mapping (TKM) Prototype. The prototype is domain-specific, the purpose of which is to map instructional text onto a knowledge domain. The context of the knowledge domain is DC electrical circuit. During development, the prototype has been tested with a limited data set from the domain. The prototype reached a stage where it needs to be evaluated with a representative linguistic data set called corpus. A corpus is a collection of text drawn from typical sources which can be used as a test data set to evaluate NLP systems. As there is no available corpus for the domain, we developed and annotated a representative corpus. The evaluation of the prototype considers two of its major components- lexical components and knowledge model. Evaluation on lexical components enriches the lexical resources of the prototype like vocabulary and grammar structures. This leads the prototype to parse a reasonable amount of sentences in the corpus. While dealing with the lexicon was straight forward, the identification and extraction of appropriate semantic relations was much more involved. It was necessary, therefore, to manually develop a conceptual structure for the domain to formulate a domain-specific framework of semantic relations. The framework of semantic relationsthat has resulted from this study consisted of 55 relations, out of which 42 have inverse relations. We also conducted rhetorical analysis on the corpus to prove its representativeness in conveying semantic. Finally, we conducted a topical and discourse analysis on the corpus to analyze the coverage of discourse by the prototype.

A Corpus-based evaluation of lexical components of a domain-specific text to Knowledge Mapping prototype

The aim of this paper is to evaluate the lexical components of a text to knowledge mapping (TKM) prototype. The prototype is domain-specific, the purpose of which is to map instructional text onto a knowledge domain. The context of the knowledge domain of the prototype is physics, specifically DC electrical circuits. During development, the prototype has been tested with a limited data set from the domain. The prototype now reached a stage where it needs to be evaluated with a representative linguistic data set called corpus. A corpus is a collection of text drawn from typical sources which can be used as a test data set to evaluate NLP systems. As there is no available corpus for the domain, we developed a representative corpus and annotated it with linguistic information. The evaluation of the prototype considers one of its two main components-lexical knowledge base. With the corpus, the evaluation enriches the lexical knowledge resources like vocabulary and grammar structure. This leads the prototype to parse a reasonable amount of sentences in the corpus.

The anatomy of an active multimodal presentation in educational contexts

This paper presents a methodology for analyzing gestures within active multimodal presentations (AMP) which are designed to produce coherently integrated communications within educational contexts. The methodology is focused on a semantic integration of the visual, verbal and gestural modalities. We identify three representational forms - a time based transcript, that is extracted from presentations to produce a speech mark-up; a concept based semantic analysis of the content; and a representation of gestures which distinguishes visual depictions of their icons, their trajectories, referents, and functions that link the verbal and visual modalities of the presentations. Our experiments are showing the utility of the analyses giving guidelines that can aid the design of AMPs within educational contexts.

Machine-Mediated Communication: The Technology

Advances in communication technology are pushing the boundaries of machine support from the pure signalling domain to the cognitive domain. This is giving rise to the new multidisciplinary approach of machine-mediated communication. In this context, machines need to be guided by a human-communication paradigm. Moreover, with a diverse interest in this emerging area of research, a unified framework is required to which we could map the various contributions made by researchers. It is argued that a classification of the different types of user-machine interactions could be a starting point. In this classification, it is proposed that any type of interface activity could be identified as one or more of four types: observation, operation, conversation or articulation

Presenting and Representing Knowledge to Develop Understanding

Using multimodality in presentations which include speech, visuals, and gestures, influences cognitive processing load and the subsequent understanding of students. However, having them produce (differing) representations of their knowledge that support descriptions, explanations and problem solving, not only aids reasoning and reflection, but gives insights into the development of the conceptualizations which underpin their understanding. An experimental study gives support to these conclusions.

Relations for Graphical Conceptual Representations

The formulation of conceptual relations is the most important part in building a conceptual representation; it is also the most demanding. Developing a framework of conceptual relations to support users in this task not only reduces the cognitive loading associated with it but also reduces the variability of expressions, a necessary condition for sharing and exchanging conceptual representations. A framework of conceptual relations is proposed grouping 31 relations under 7 categories that fall within 4 main themes: taxonomy/hierarchy, organization, space & time and action-based relations.

A Case Study on Using Conceptual Mapping

This paper reports on work in progress in relation to the use of conceptual mapping to support deep and analytical thinking in developing project proposals. In addition to testing the role of conceptual mapping, a new framework for constructing conceptual maps is also being evaluated in this study. This research takes the form of a case study based on a module being taught at a second year undergraduate programme.

A Framework for Using Semantic Relations in Conceptual Structures

This paper builds on the fact that generating a good conceptual structure depends on using appropriate semantic relations. To support this process, a model-based framework that distinguishes between instances of semantic relations and their generic form is proposed. The framework puts the generic forms at the base of a hierarchy that includes type and context.

Cognitive Support for Conceptual Acquisition through Reading

Cognitive support for conceptual acquisition through reading is quite limited in current computer-supported reading environments. In this paper, we describe a new approach, the CogTool, to support the cognitive processes associated with reading. It involves the use of semantic structures and related functions to support the cognitive operations of interpretation through to the acquisition and integration of new concepts into existing knowledge.

Communication and Design in Multimodal Presentations

Effective educational presentations not only communicate meaning through structured content, but indicate the attitudes of presenters and their empathic engagement with the audience. This paper considers the design of multimodal presentations, specifically examining the functional and integrative roles of gestures in the communicative process when materials are presented by experienced teachers. A gestural coding scheme is used to describe similarities and differences between the presenters when dealing with the same topics under three presentation formats. These data give useful insights into how the visual, verbal and gestural modalities are used to effect communicative and educational intentions.