NAACL-HLT 2019: News Article Teaser Tweets and How to Generate Them, Minneapolis, USA, June 2nd, 2019
Abstract: We define the task of teaser generation and provide an evaluation benchmark and baseline systems for it. A teaser is a short reading suggestion for an article that is illustrative and includes curiosity-arousing elements to entice potential readers to…
Talk/Panel: Trust and Responsibility in Industrial Artificial Intelligence, HSG Alumni Deutschland Konferenz, Frankfurt, 4-6th April 2019
#TrustReloaded – the main theme of the HSG A. Alumni Deutschland Konferenz 2019 in Frankfurt. #Algorithms play a big role in business decisions. That’s why it needs „best practices“ for managers how to mitigate the risks and profit from the…
Frankfurter Allgemeine Zeitung: Wie Künstliche Intelligenz der Industrie hilft 2018
Seit mehr als 20 Jahren arbeitet Siemens mit Künstlicher Intelligenz. Vergangenes Jahr hat der Konzern ein eigenes KI-Labor eröffnet. Doch ein Schulbus und ein Vogelstrauß zeigen, dass noch viel zu tun ist… Nice article about our work at Siemens AI…
Meetup: Artificial Intelligence & the Creative State of Mind, June 19th 2018, Munich
Creativity is a fundamental aspect of human intelligence and an interesting challenge for AI. Are Machine Learning and AI technologies capable of Creativity? New artificial intelligence systems are using techniques such as generative adversarial networks to develop creativity and originality…
End-to-End Trainable Attentive Decoder for Hierarchical Entity Classification
Abstract: We address fine-grained entity classification and propose a novel attention-based recurrent neural network (RNN) encoderdecoder that generates paths in the type hierarchy and can be trained end-to-end. We show that our model performs better on fine-grained entity classification than…
Reports on the 2014 AAAI Fall Symposium Series
Abstract: The AAAI 2014 Fall Symposium Series was held Thursday through Saturday, November 13–15, at the Westin Arlington Gateway in Arlington, Virginia adjacent to Washington, DC. The titles of the seven symposia were Artificial Intelligence for Human-Robot Interaction, Energy Market…
Ontology-based translation of natural language queries to SPARQL
Abstract: We present an implemented approach to transform natural language sentences into SPARQL, using background knowledge from ontologies and lexicons. Therefore, eligible technologies and data storage possibilities are analyzed and evaluated. The contributions of this paper are twofold. Firstly, we…
Smart Data Access: Semantic Web Technologies for Energy Diagnostics
Abstract: In today‘s (big) data-intensive world, scalable technologies enabling the efficient management, storage and analysis of large data set are needed. However, the underlying logic of the emerging data-driven business is very different to the established understanding of the traditional…
LinkedHealthAnswers: Towards Linked Data-driven Question Answering for the Health Care Domain
Abstract: This paper presents Linked Health Answers, a natural language question answering systems that utilizes health data drawn from the Linked Data Cloud. The contributions of this paper are three-fold: Firstly, we review existing state-of-the-art NLP platforms and components, with a special…
Natural Language Access to Enterprise Data
Abstract:This paper describes USI Answers — a natural language question answering system for enterprise data. We report on the progress towards the goal of offering easy access to enterprise data to a large number of business users, most of whom…
