In this paper the use of model building for natural language understanding in practical systems is investigated. After outlining several interpretation tasks where model construction would be useful, we perform experiments using two state-of-the-art model builders on the interpretation of imperatives in discourse. The results are acceptable for small discourses and small domains, but don’t scal...

This article introduces TableMiner, the first semantic Table Interpretation method able to annotate Web tables using an incremental, bootstrapping learning approach seeded by automatically selected ‘partial’ content from tables. The basic principle is to create initial and partial annotations of a table using some as opposed to all content in the table. The partial outcome then serves as ‘stepp...

DIAS is an Asynchronous Discussion Forum Software, mainly developed in order to offer extended monitoring and interaction analysis support, by providing a wide range of indicators jointly used in various situations, to all discussion forae users (individual students, groups, moderators/teachers or even researchers/observers), appropriate for their various roles in different activities. In this ...

A modiication to neural network training algorithms is proposed which decorrelates certain weights within the network while minimising the mean squared error. The technique was developed to facilitate neural network interpretation in image processing problems, partly by allowing to initialise all network weights with one xed, low value. However, it can also be applied to classiica-tion tasks in...

In this paper, we propose a method for the analysis and the interpretation of the interactions between the user and the interactive system to evaluate. The proposed approach is based on the comparison between the user interaction sequences and the sequences average. This confrontation concerns the task execution duration, the realized tasks number and the action sequence used in a defined exper...

In this paper we discuss the importance of scene registration for several tasks in the automated interpretation of aerial imagery. These tasks are structure matching, stereo matching, and stereo visualization. While the processes of registration and matching have traditionally been treated as separate problems, particularly in the case of stereo matching, we describe techniques that may unify t...

Online learning provides the potential for more differentiated, integrated, and open learning environments to solve team project assignments. We argue that although it is feasible to increase information richness via adopting multimedia technologies, the effectiveness to promote interpersonal skills, critical thinking, and cognitive learning processes via virtual group discussion is uncertain. ...

In this paper, we present an integrated model of the two central tasks of dialog management: interpreting user actions and generating system actions. We model the interpretation task as a classication problem and the generation task as a prediction problem. These two tasks are interleaved in an incremental parsing-based dialog model. We compare three alternative parsing methods for this dialog...

This article is a survey of methods for measuring agreement among corpus annotators. It exposes the mathematics and underlying assumptions of agreement coefficients, covering Krippendorff’s alpha as well as Scott’s pi and Cohen’s kappa; discusses the use of coefficients in several annotation tasks; and argues that weighted, alpha-like coefficients, traditionally less used than kappa-like measur...

Humans learn from teachers by observing gestures, reinforcements, and words, which we collectively call signals. Often a new signal will support a different interpretation of an earlier signal, resulting in a different belief about the task being learned. If robots are to learn from these signals, they must perform similar inferences. We propose the use of Bayesian inference to allow robots to ...