Current Projects

Current Projects

Experimental software from the research projects of UKP can be found at GitHub: https://github.com/ukplab

German Research Foundation (DFG)

Evidence

Dictionaries are an essential resource in many domains of research, education, and natural language processing (NLP). One crucial part of dictionaries are example sentences which illustrate real-world use cases of a lemma. However, finding good example sentences in large corpora imposes a heavy workload on lexicographers. In this project, we develop a novel system which eases the work of lexicographers by interactively assessing the goodness and diversity of dictionary examples.

INCEpTION: Towards an Infrastructure for the Distributed Exploration and Annotation of Large Corpora and Knowledge Bases

The annotation of specific semantic phenomena often require compiling task-specific corpora and creating or extending task-specific knowledge bases. Presently, researchers require a broad range of skills and tools to address such semantic annotation tasks. INCEpTION aims towards building an annotation platform that incorporates corpus extraction, annotation, and knowledge management into a joint platform.

Informatik selbstgemacht! (computer science self-made!)

Funded by AIPHES, this workshop for pupils in 6th/7th grade promotes women in STEM. Lead by female computer science students from TU Darmstadt, the pupils gain some data analytics and programming skills.

Information Consolidation: A New Paradigm in Knowledge Search (DIP project)

The DIP project – an international cooperation with Bar-Ilan University and Israel Institute of Technology – aims at the next big step in information access technology. The goal is to support users in identifying and assimilating the large set of relevant statements found within multitudes of documents which are usually retrieved by the current search technologies. Novel methods for statement extraction, information consolidation, and inferring relations represent the core research areas within this project.

Research Training Group AIPHES (“Adaptive Information Preparation from Heterogeneous Sources”), DFG GRK 1994

AIPHES develops new methods to deal with information overload by summarizing multiple documents to a condensed summary. We develop adaptive methods to create summaries of any type from multiple sources and across different genres. To do so, we combine different methodological backgrounds – computational linguistics, computer science, machine learning – to approach the task of extracting, summarizing and evaluating textual information from different sources.

Open Argument Mining

This project aims at investigating computational methods that continuously improve their capability to recognize arguments in ongoing debates, align incomplete arguments with previous arguments and enrich them with automatically acquired background knowledge, and constantly extend semantic knowledge bases with information required to understand arguments.

Federal Ministry of Education and Research (BMBF)

Decision Support by Means of Automatically Extracting Natural Language Arguments from Big Data

In order to make informed decisions, appropriate arguments are needed. However, the mere amount of information and the complexity of many questions frequently prevents us from finding all arguments that are relevant for a reasonable decision. Within the “Decision support by means of automatically extracting natural language arguments from big data” (ArgumenText) project, the UKP Lab develops novel Argument Mining methods for extracting arguments from large and heterogeneous text sources in order to facilitate decision making processes. In response to a user-defined search query, neural networks determine relevant arguments in realtime and summarize them in a comprehensive way. In contrast to conventional systems, an argumentative information system can show the reasons for or against a decision.

SenPAI-Security and Privacy in AI

SenPAI addresses the subject of security and ML from two perspectives: The first perspective is improving the security of ML algorithms and systems based on ML. This does not include standard system security, which is a generic requirement for all IT systems. The focus is on security challenges that are especially and in some cases exclusively relevant to ML. The term “security” has to be seen in a broad sense here, as issues like privacy leakage or transparency of decisions shall also be addressed. The second perspective is application-centric. As CRISP has a focus on applied security solutions, in the project new security applications based on ML are to be developed and evaluated. These applications can and shall also utilize the security mechanisms developed in the technology-centric research projects and give a feedback on their usability and performance. The application-centric projects also can raise new challenges for the technology-centric projects. These projects will also potentially be Big Data projects due to their handling of complex data and their aim to efficiently derive information relevant for security matters from it.

Loewe Research Center Digital Humanities (State of Hesse)

emergenCITY

In 2050, roughly two-thirds of the world population are expected to live in urban areas. The sustainable growth in number and size of cities is only possible due to gains in efficiency in (critical) infrastructures such as energy, transportation, logistics, and water. Information and communication technology (ICT) is the main driver behind these efficiency gains and acts as the enabler for digital cities. However, this trend also poses a threat to the functioning of cities in crisis situations. Increasing interconnectedness and dependence on digital services make societies more vulnerable to disruptive events that impact on regular ICT functions. ICT-based infrastructures are at peril due to man-made or natural disasters, violence and terror. At the same time, the Functioning of digital cities is not well understood in cases of extreme events, crises, and catastrophes. emergenCITY aims to investigate fundamentals, methods and solutions towards enabling so-called „Resilient Digital Cities“. With this, we refer to the resilience of future digital cities and the capability of ICT and its users to resist, adapt, and transform in crisis situations.

Software Campus (BMBF)

Software Campus program is funded by Germany's Federal Ministry for Education and Research (BMBF).

In close collaboration with strong partners from industry and research, Software Campus participants develop innovative academic IT projects and benefit from an individually tailored training curriculum with outstanding academics and managers. The Federal Ministry of Education and Research (BMBF) provides funding of up to EUR 100,000 for each IT project.

UKP Lab is currently represented in the network by the following researchers:

The projects already finished within the scope of the program: