Do bridges dream of water pollutants? Towards DreamsKG, a knowledge graph to make digital access for sustainable environmental assessment come true Darío Garigliotti Johannes Bjerva Finn Årup Nielsen Aalborg University, Denmark Aalborg University, Denmark DTU, Denmark dariog@cs.aau.dk jbjerva@cs.aau.dk faan@dtu.dk Annika Butzbach Ivar Lyhne Lone Kørnøv Aalborg University, Denmark Aalborg University, Denmark Aalborg University, Denmark annikab@plan.aau.dk lyhne@plan.aau.dk lonek@plan.aau.dk Katja Hose Aalborg University, Denmark khose@cs.aau.dk TU Wien, Austria katja.hose@tuwien.ac.at ABSTRACT An environmental assessment (EA) report describes and assesses the environmental impact of a series of activities involved in the development of a project. As such, EA is a key tool for sustainability. Improving information access to EA reporting is a billion-euro untapped business opportunity to build an engaging, efcient digital experience for EA. We aim to become a landmark initiative in making this experience come true, by transforming the traditional manual assessment of numerous heterogeneous reports by experts into a computer-assisted approach. Specifcally, a knowledge graph that represents and stores facts about EA practice allows for what it is so far only accessible manually to become machine-readable, and by this, to enable downstream information access services. This paper describes the ongoing process of building DreamsKG, a knowledge graph that stores relevant data- and expert-driven EA reporting and practicing in Denmark. Representation of cause- efect relations in EA and integration of Sustainable Developmental Goals (SDGs) are among its prominent features. KEYWORDS Knowledge graphs, Knowledge graph construction, Sustainability, Cause-efect relations ACM Reference Format: Darío Garigliotti, Johannes Bjerva, Finn Årup Nielsen, Annika Butzbach, Ivar Lyhne, Lone Kørnøv, and Katja Hose. 2023. Do bridges dream of water pollutants? Towards DreamsKG, a knowledge graph to make digital access for sustainable environmental assessment come true . In Companion Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for proft or commercial advantage and that copies bear this notice and the full citation on the frst page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specifc permission and/or a fee. Request permissions from permissions@acm.org. WWW ’23 Companion, April 30–May 04, 2023, Austin, TX, USA © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM. ACM ISBN 978-1-4503-9419-2/23/04. . . $15.00 https://doi.org/10.1145/3543873.3587590 Proceedings of the ACM Web Conference 2023 (WWW ’23 Companion), April 30–May 04, 2023, Austin, TX, USA. ACM, New York, NY, USA, 7 pages. https://doi.org/10.1145/3543873.3587590 1 INTRODUCTION The interest for making digital access a reality for large corpora of documents, abundant in textual content within many organiza- tions and sectors, has extended the application cases of Information Extraction (IE) technologies to a variety of domains with hetero- geneous data formats, including legal documents [22], gastron- omy [23], fnancial reports [3, 20], and public crisis response [10]. More recently, IE applications have embraced modalities beyond text [8, 16] and within scenarios where scarcity meets data-hungry methods [20]. Environmental assessment (EA), although involving this kind of data phenomena, is still dominated by traditional prac- tices, heavy on tedious, expert human labor. Large volumes of tech- nical reports, highly heterogeneous and rich in EA content, make this area one of enormous potential for developing digital access to this vast amount of information. And being EA a legal requirement in most countries world-wide, developing such a sustainable digital transformation can have very large social and economical impact. Beyond a very few works in this area [6, 19], the lack of knowledge resources available is a key challenge to enable building digital access experiences for sustainable EA. DREAMS 1 is an interdisciplinary project aiming to provide dig- ital support for environmental assessment. In the context of this project, at the core of powering the future of digital access experi- ence for EA, we place DreamsKG, a knowledge graph intended to represent and store facts about EA practice so far only accessible manually in the mostly textual content of numerous heterogeneous reports. We aim to tackle the challenge of building such a key knowl- edge resource in a domain where this kind of resources are very scarce. By building DreamsKG, we have at hand a resource that can power digital information access services that come to transform the traditionally manual practices of EA professionals. In particular, 1 https://dreamsproject.dk/ 724