emergenCITY
(Funding Period: 2020 - 2023)

Emergency Responsive Digital Cities

Motivation

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.

Goals

This project addresses the processing of information, which is initially not compatible for computer analysis, such as written and spoken language, visual information etc. The project focuses on two aspects:

  • cross-modality, i.e. integrated processing of different forms of information and sources, and
  • cross-timescale integration, i.e. from emergency response in real-time to long-term data (data at rest) that can support preparation for future crises.

Team

  • Prof. Dr. Iryna Gurevych, Principal Investigator
  • Jonas Pfeiffer

Partners

emergenCITY is organized as an interdisciplinary and multi-site cooperation involving the university partners Technische Universität Darmstadt, Universität Kassel and Philipps-Universität Marburg. In addition, the associated partners, the Federal Office for Civil Protection and Disaster Relief (BBK) and the City of Darmstadt are also involved in the center.

Funding

EmergenCITY is funded by the 12th “Landes-Offensive zur Entwicklung wissenschaftlich-ökonomischer Exzellenz” (LOEWE) (state offensive for the development of scientific and economic excellence), with a funding period from 2020 to 2023. LOEWE is the research promotion program of the federal state of Hessen, Germany. Established in 2008 it aims to set research policy trends and to give a sustainable boost to Hesse’s research landscape. LOEWE funds excellent research projects and especially the cooperation between academia, non-university research institutes and businesses.

Publications

Steitz, Jan-Martin O. ; Pfeiffer, Jonas ; Gurevych, Iryna ; Roth, Stefan (2021):
TxT: Crossmodal End-to-End Learning with Transformers.
DAGM German Conference on Pattern Recognition 2021, Virtual Conference, 28.09.-01.10.2021, [Conference or Workshop Item]

Ribeiro, Leonardo F. R. ; Pfeiffer, Jonas ; Zhang, Yue ; Gurevych, Iryna (2021):
Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation.
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 742-750,
ACL, 2021 Conference on Empirical Methods in Natural Language Processing, virtual Conference and Punta Cana, Dominican Republic, 07.-11.11.2021, ISBN 978-1-955917-09-4,
[Conference or Workshop Item]

Pfeiffer, Jonas ; Vulić, Ivan ; Gurevych, Iryna ; Ruder, Sebastian (2021):
UNKs Everywhere: Adapting Multilingual Language Models to New Scripts.
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 10186-10203,
ACL, The 2021 Conference on Empirical Methods in Natural Language Processing, virtual Conference and Punta Cana, Dominican Republic, 07.- 11.11.2021, ISBN 978-1-955917-09-4,
[Conference or Workshop Item]

Poth, Clifton ; Pfeiffer, Jonas ; Rücklé, Andreas ; Gurevych, Iryna (2021):
What to Pre-Train on? Efficient Intermediate Task Selection.
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 10585-10605,
ACL, The 2021 Conference on Empirical Methods in Natural Language Processing, virtual Conference and Punta Cana, Dominican Republic, 07.- 11.11.2021, ISBN 978-1-955917-09-4,
[Conference or Workshop Item]

Rücklé, Andreas ; Geigle, Gregor ; Glockner, Max ; Beck, Tilman ; Pfeiffer, Jonas ; Reimers, Nils ; Gurevych, Iryna (2021):
AdapterDrop: On the Efficiency of Adapters in Transformers.
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 7930-7946,
ACL, The 2021 Conference on Empirical Methods in Natural Language Processing, virtual Conference and Punta Cana, Dominican Republic, 07.-11.11.2021, ISBN 978-1-955917-09-4,
[Conference or Workshop Item]

Pfeiffer, Jonas ; Kamath, Aishwarya ; Rücklé, Andreas ; Cho, Kyunghyun ; Gurevych, Iryna (2021):
AdapterFusion: Non-Destructive Task Composition for Transfer Learning.
In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 487-503,
ACL, 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021), virtual conference, 19.-23.04.2021, ISBN 978-1-954085-02-2,
[Conference or Workshop Item]

Rücklé, Andreas ; Pfeiffer, Jonas ; Gurevych, Iryna (2020):
MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale.
In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 2471-2486,
Association for Computational Linguistics, 2020 Conference on Empirical Methods in Natural Language Processing, virtual Conference, 16.-20.11.2020, ISBN 978-1-952148-60-6,
DOI: 10.18653/v1/2020.emnlp-main.194,
[Conference or Workshop Item]

Kuznetsov, Ilia ; Gurevych, Iryna (2020):
A Matter of Framing: The Impact of Linguistic Formalism on Probing Results.
pp. 171-182, Association for Computational Linguistics, The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), virtual Conference, 16.-20.11., [Conference or Workshop Item]