Open Information Extraction (OIE) is a well performing intermediate step for tasks like summarization, text comprehension relation extraction or knowledge base construction. However, there is surprisingly little work on evaluating and on comparing different methods. How can we compare results of existing OIE systems?
Textual data is a core source of information in the enterprise. Example demands arise from sales departments (monitor and identify leads), human resources (identify professionals with capabilities in “xyz”), market research (campaign monitoring from the social web), product development (incorporate feedback from customers), supply chain management.
Cognitive disability may lead to learning difficulties, difficulties in problem solving, concentration and attention problems, poor orientation capability. Accessibility for users with cognitive disabilities is a great challenge. So far in our work on interactive Web and human computing, we have focused on eye-brain interfaces and how it can assist the people with motor disability.
The Web has become part of our all-day life, but its access is limited to either mouse and keyboard or touch based input devices. The technical development of eye tracking systems over the recent years makes them affordable and act as an exciting opportunity to include people with disabilities into the modern digital environment.
Currently there is a shortage of citation data for the social sciences and especially for the German social sciences. The EXCITE project aims to close this gap by automatically extracting such information from a large available corpus of research papers. A step towards this goal is to construct a gold standard which allows an evaluation of the different steps in the extraction pipeline.
Data access is tricky and error-prone. Many formats require a deep understanding of the underlying techniques to be accessible. Additionally, the access itself is often error-prone due to unchecked queries or simply wrong assumptions while processing query results.
In concept lattice-based information retrieval, the task of document retrieval is being supported by means of Formal Concept Analysis. The steps of query matching and document ranking are informed by an underlying concept lattice thus induced from a set of documents. Recently, Codocedo et al. proposed a refined approach to this using semantic similarity as the basis for query evaluation and document ranking. This talk will give an introduction to their approach and discuss evaluation results.
In order to make statements about resources like people, websites or documents, the Resource Description Framework (RDF) is used. RDF data is represented as subject-predicate-object triples, where the subject is the described resource, the predicate is the defined property and the object.
In the context of the SemGIS project we are in need of data that fulfils the requirements we need to fulfil the usecases of our project partners. Currently, we would like to rely on OpenData only in order to find make predictions in our usecases of disaster management and energy.
Not all edges are of the same importance in a graph. However, previous research works have been focusing on vertices rather than edges. We propose a method that can measure the importance of edges, given a undirected simple graph (edges are unweighted). Such method can be easily extended to work with directed graphs as well. We also show evaluation results, how we identify important edges in a graph. Applications of the method are to be discussed.