Orchestrating NLP Services for the Legal Domain

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 2332–2340 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 2332 Orchestrating NLP Services for the Legal Domain Juli´an Moreno-Schneider1, Georg Rehm1, Elena Montiel-Ponsoda2, V´ıctor Rodr´ıguez-Doncel2, Artem Revenko3, Sotirios Karampatakis3, Maria Khvalchik3, Christian Sageder4, Jorge Gracia5, Filippo Maganza6 1 DFKI GmbH, Germany – 2 Universidad Polit´ecnica de Madrid, Spain – 3 Semantic Web Company GmbH, Austria 4 Openlaws GmbH, Austria – 5 Universidad de Zaragoza, Spain – 6 Alpenite, Italy Corresponding author: Juli´an Moreno Schneider – julian.moreno schneider@dfki.de Abstract Legal technology is currently receiving a lot of attention from various angles. In this contribution we describe the main technical components of a system that is currently under development in the European innovation project Lynx, which includes partners from industry and research. The key contribution of this paper is a workflow manager that enables the flexible orchestration of workflows based on a portfolio of Natural Language Processing and Content Curation services as well as a Multilingual Legal Knowledge Graph that contains semantic information and meaningful references to legal documents. We also describe different use cases with which we experiment and develop prototypical solutions. Keywords: Text Analytics, Tools, Systems, Applications, Knowledge Discovery/Representation 1. Introduction We present a methodology and tooling to handle a set of various Natural Legal Language Processing and Document Curation services currently under development in the EU project Lynx1. First, the platform is acquiring data and doc- uments related to compliance from jurisdictions in different languages with a focus on English, Spanish, German, and Dutch along with terminologies, dictionaries and other lan- guage resources. Based on this collection of structured data and unstructured documents we create a multilingual Le- gal Knowledge Graph (LKG), represented as Linked Data. Second, a set of flexible language processing services is de- veloped to analyse and process the data and documents to integrate them into the LKG. Semantic processing compo- nents annotate, structure, and interlink the LKG contents. The following research challenges arose during the project: (i) How to efficiently orchestrate a set of NLP services? How to guarantee their interchangeability? (ii) How to efficiently extract information and store docu- ments along with the extracted information? (iii) In which business scenarios are legal NLP services able to generate actual added value? The remainder of this article is structured as follows. Section 2 describes different use cases, addressing chal- lenge (iii), while Section 3 focuses upon the LKG used in the prototype applications, addressing challenge (ii). The infrastructure, semantic services and their orchestra- tion through the content and document curation workflow manager, is described in Section 4, addressing challenge (i). After a brief review of related work (Section 5) we sum- marise the paper and describe future work (Section 6). 1http://lynx-project.eu 2. Use Cases The following three briefly sketched use cases illustrate the development work in the project. The pilot initiatives de- scribed next are still not operational, but the current efforts will make them operational in the …

Content truncated to 500 words