Search results for "RETRIEVAL"

Machine Learning and Knowledge Discovery in Databases. Research Track

2021

Automated Creation of Expert Systems with the InteKRator Toolbox

2021

Expert systems have a long tradition in both medical informatics and artificial intelligence research. Traditionally, such systems are created by implementing knowledge provided by experts in a system that can be queried for answers. To automatically generate such knowledge directly from data, the lightweight InteKRator toolbox will be introduced here, which combines knowledge representation and machine learning approaches. The learned knowledge is represented in the form of rules with exceptions that can be inspected and that are easily comprehensible. An inference module allows for the efficient answering of queries, while at the same time offering the possibility of providing explanation…

A Semantic Layer on Semi-structured Data Sources for Intuitive Chatbots

2009

The main limits of chatbot technology are related to the building of their knowledge representation and to their rigid information retrieval and dialogue capabilities, usually based on simple "pattern matching rules". The analysis of distributional properties of words in a texts corpus allows the creation of semantic spaces where represent and compare natural language elements. This space can be interpreted as a "conceptual" space where the axes represent the latent primitive concepts of the analyzed corpus. The presented work aims at exploiting the properties of a data-driven semantic/conceptual space built using semi-structured data sources freely available on the web, like Wikipedia. Thi…

A Comparison of Language Identification Approaches on Short, Query-Style Texts

2010

In a multi-language Information Retrieval setting, the knowledge about the language of a user query is important for further processing. Hence, we compare the performance of some typical approaches for language detection on very short, query-style texts. The results show that already for single words an accuracy of more than 80% can be achieved, for slightly longer texts we even observed accuracy values close to 100%.

Enriching Didactic Similarity Measures of Concept Maps by a Deep Learning Based Approach

2021

Concept maps are significant tools able to support several tasks in the educational area such as curriculum design, knowledge organization and modeling, students' assessment and many others. They are also successfully used in learning activities in which students have to represent domain knowledge according to teacher's assignment. In this context, the development of Learning Analytics approaches would benefit of methods that automatically compare concept maps. Detecting concept maps similarities is relevant to identify how the same concepts are used in different knowledge representations. Algorithms for comparing graphs have been extensively studied in the literature, but they do not appea…

Comparing Translation and Post-editing: An Annotation Schema for Activity Units

2016

The current chapter introduces an annotation schema of TPR data that categorises post-editing behaviour into five different classes and compares general-language and domain-specific English-to-German translation and post-editing with respect to production times, key-logging (text production activity and text elimination activity) and eye-tracking data (total reading times on source text and on target text). The results support the hypothesis that post-editing is faster than translation from scratch for both domain-specific and non-domain-specific text types. When key-logging and eye-tracking data are taken into consideration, domain-specific texts require more effort when translating from s…

Związek między jakością informacji w serwisach WWW związanych ze zdrowiem a ich rankingami

2015

Meter for the Quantitative Analysis of Newspaper Sport Material

2016

This article presents a meter for the quantitative analysis of newspaper sport material. The meter makes it possible to measure and classify newspaper sport material in detail. The meter has three levels. The selected level depends on the research purpose and desired measurement accuracy. Measurement can focus on a certain level, or all levels can be used together. Individual variables can also be utilized at a certain level. The three levels with respective level units of observation are: 1) articles, photos, and graphics; 2) sets of articles; and 3) sets of data materials. The use of each level is presented in the article. The article also contains a summary of the newspaper sport materia…

A P2P Architecture for Multimedia Content Retrieval

2006

The retrieval facilities of most Peer-to-Peer (P2P) systems are limited to queries based on unique identifiers or small sets of keywords. This approach can be highly labor-intensive and inconsistent. In this paper we investigate a scenario where a huge amount of multimedia resources are shared in a P2P network, by means of efficient content-based image and video retrieval functionalities. The challenge in such systems is to limit the number of sent messages, maximizing the usefulness of each peer contacted in the query process. We achieve this goal by the adoption of a novel algorithm for routing user queries. The proposed approach exploits compact representations of multimedia resources sh…

A Taxonomy as a Vehicle for Learning

2009

In this article, we describe the development of a classification system providing a framework for analysis of, and communication about, a subgroup of learning objects. The objects we consider are highly visual, animated, interactive, and mathematics-related, and we call them VaniMaps. Secondly, we discuss the use of the system. In the first phase, the development was based on literature studies and discussions on examples of VaniMaps. In the second phase, the classification system was tested by students and their responses were analyzed to identify possible improvements. Now, the system is developed further based on experience gained while using it for different purposes. We see several pos…