Filters








256 Hits in 4.4 sec

Orchestrating NLP Services for the Legal Domain [article]

Julián Moreno-Schneider and Georg Rehm and Elena Montiel-Ponsoda and Víctor Rodriguez-Doncel and Artem Revenko and Sotirios Karampatakis and Maria Khvalchik and Christian Sageder and Jorge Gracia and Filippo Maganza
2020 arXiv   pre-print
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.  ...  Acknowledgments This work has been partially funded by the project LYNX, which has received funding from the EU's Horizon 2020 research and innovation programme under grant agreement no. 780602, see http  ... 
arXiv:2003.12900v1 fatcat:vlejc7mkqfh6fnh4bt6huspiym

LYNX: Towards a Legal Knowledge Graph for Multilingual Europe

Víctor Rodríguez Doncel, Elena Montiel Ponsoda
2020 Law in context (Bundoora, Vic.)  
Lynx is an innovation project in Europe whose objective is to develop services for legal compliance.  ...  Three use cases are discussed, as well as the overall impact of the project.  ...  Population workflows orchestrating these services have been put in place (Schneider et al. 2018 and 2020): original documents have been annotated with these NLP-based services, uniformly structured and  ... 
doi:10.26826/law-in-context.v37i1.129 fatcat:psdbemq5nvgphd55nbu5xo2fnu

SCMS – Semantifying Content Management Systems [chapter]

Axel-Cyrille Ngonga Ngomo, Norman Heino, Klaus Lyko, René Speck, Martin Kaltenböck
2011 Lecture Notes in Computer Science  
In addition, it relies on the RDF and HTTP standards for communication and can thus be integrated in virtually any CMS. We present how our framework is being used in the energy sector.  ...  Yet, there is still a blatant need for frameworks that can be easily integrated into CMS and allow to transform their content into machine-readable knowledge with high accuracy.  ...  name cannot be revealed for legal reasons.  ... 
doi:10.1007/978-3-642-25093-4_13 fatcat:itnp3lmb5jcgpaayxebfpvo7li

A Workflow Manager for Complex NLP and Content Curation Pipelines [article]

Julián Moreno-Schneider, Peter Bourgonje, Florian Kintzel, Georg Rehm
2020 arXiv   pre-print
We present a workflow manager for the flexible creation and customisation of NLP processing pipelines.  ...  The workflow manager addresses challenges in interoperability across various different NLP tasks and hardware-based resource usage.  ...  Acknowledgements The work presented in this paper has received funding from the German Federal Ministry of Education and Research (BMBF) through the project QURATOR (Wachstumskern no. 03WKDA1A) as well  ... 
arXiv:2004.14130v1 fatcat:y5p4hkts7bczhf65lvcets7dl4

Lynx Newsletter issue #2: Webinars registration, events and achievements [article]

Lynx Consortium
2020 Zenodo  
This post addresses the requirements posed by legal consultancy experts and how the consortium has designed and implemented the Lynx Services Platform (LynxSP).  ...  In this video, Elena Montiel-Ponsoda, as project coordinator, explains the challenges that the consortium faced and the features that will bring the Lynx Services beyond the state-of-the-art.  ...  Lynx Webinar Series Geothermal Energy is an emerging source of Lynx Service Platform architecture Orchestrating legal NLP services for a portfolio of use cases "In this post, I focus on general usage scenarios  ... 
doi:10.5281/zenodo.4723455 fatcat:xgb77cdy5ncc5mo43g6yevar2i

The Language Application Grid [chapter]

Nancy Ide, James Pustejovsky, Christopher Cieri, Eric Nyberg, Denise DiPersio, Chunqi Shi, Keith Suderman, Marc Verhagen, Di Wang, Jonathan Wright
2016 Lecture Notes in Computer Science  
It is based on the service-oriented architecture (SOA), a more recent, web-oriented version of the "pipeline" architecture that has long been used in NLP for sequencing loosely-coupled linguistic analyses  ...  The transformative aspect of the LAPPS Grid is that it orchestrates access to and deployment of language resources and processing functions available from servers around the globe and enables users to  ...  21 , which provides an interface to UIMA-based components primarily for the Biomedical domain.  ... 
doi:10.1007/978-3-319-31468-6_4 fatcat:3df2ncw25rdzrepd7worxhrvfq

A Lightweight API-Based Approach for Building Flexible Clinical NLP Systems

Zhengru Shen, Hugo van Krimpen, Marco Spruit
2019 Journal of Healthcare Engineering  
It takes NLP as an external component which can be accessed independently and orchestrated in a pipeline via web APIs.  ...  Natural language processing (NLP) has become essential for secondary use of clinical data. Over the last two decades, many clinical NLP systems were developed in both academia and industry.  ...  Acknowledgments is work is part of the project "OPERAM: OPtimising thERapy to prevent Avoidable hospital admissions in the  ... 
doi:10.1155/2019/3435609 pmid:31511785 pmcid:PMC6714318 fatcat:p4ofmq7oabbk5cqneh4ttiotny

Towards Intelligent Context-Aware 6G Security [article]

André N. Barreto, Stefan Köpsell, Arsenia Chorti, Bertram Poettering, Jens Jelitto, Julia Hesse, Jonathan Boole, Konrad Rieck, Marios Kountouris, Dave Singelee, Kumar Ashwinee
2021 arXiv   pre-print
The path towards this vision and some of the challenges along the way are discussed in this contribution.  ...  As future networks of intelligent objects come to life, tremendous new challenges arise for security, but also new opportunities, allowing to address current, as well as future, pressing needs.  ...  need for large security and legal departments, where users could enjoy new services without engaging with cumbersome and error-prone security and privacy settings in a longer-term vision of fully automated  ... 
arXiv:2112.09411v1 fatcat:ynadpp5oobh4dpmz7ku2tgaklu

Terme-à-LLOD: Simplifying the Conversion and Hosting of Terminological Resources as Linked Data

Maria Pia Di Buono, Philipp Cimiano, Mohammad Fazleh Elahi, Frank Grimm
2020 Zenodo  
Further, we discuss how the implementation of our paradigm can be integrated into existing NLP service infrastructures that rely on virtualization technology.  ...  We provide a proof-of-concept for this paradigm showing how to apply it to the conversion of the well-known IATE terminology as well as to various smaller terminologies.  ...  Teanga is a linked data based platform for natural language processing (NLP) which enables the use of many NLP services from a single interface (Ziad et al., 2018) .  ... 
doi:10.5281/zenodo.3896813 fatcat:j6qgjomr6rcm3l4ubzof66x4ka

Research challenges in nextgen service orchestration

Luis M. Vaquero, Felix Cuadrado, Yehia Elkhatib, Jorge Bernal-Bernabe, Satish N. Srirama, Mohamed Faten Zhani
2019 Future generations computer systems  
These changes bring new requirements for service orchestrators, which need to evolve so as to support new scenarios where a close interaction between service and infrastructure becomes essential to deliver  ...  Here, we present the challenges brought forward by this new breed of technologies and where current orchestration techniques stand with regards to the new challenges.  ...  Acknowledgements The authors thank Gordon S Blair for his insightful comments on prior versions of this manuscript.  ... 
doi:10.1016/j.future.2018.07.039 fatcat:x3zrha4nt5ggpdvn3p3f7cki3y

Research Challenges in Nextgen Service Orchestration [article]

Luis M. Vaquero and Felix Cuadrado and Yehia Elkhatib and Jorge Bernal-Bernabe and Satish N. Srirama and Mohamed Faten Zhani
2018 arXiv   pre-print
These changes bring new requirements for service orchestrators, which need to evolve so as to support new scenarios where a close interaction between service and infrastructure becomes essential to deliver  ...  Here, we present the challenges brought forward by this new breed of technologies and where current orchestration techniques stand with regards to the new challenges.  ...  Acknowledgement The authors thank Gordon S Blair for his insightful comments on prior versions of this manuscript.  ... 
arXiv:1806.00764v2 fatcat:a6nj556s6zaldhktwux3j4iswe

Lynx D3.5 Initial platform prototype

Filippo Maganza
2019 Zenodo  
With regards to the first point, two important internal milestones have been achieved: The format for representing documents and annotations has been defined, this is the NLP Interchange Format (NIF).  ...  As for the second point, this document tackles the problem of long-running REST services, and suggests several strategies that can be adopted in such situations to develop a fault-tolerant system.  ...  not enough for representing all enriching information in documents for the legal domain.  ... 
doi:10.5281/zenodo.3558245 fatcat:52y6qsdzynaepmu323rxos3bei

European Language Grid: An Overview

Rehm. Georg, Maria Berger, Ela Elsholz, Stefanie Hegele, Florian Kintzel, Katrin Marheinecke, Stelios Piperidis, Miltos Deligiannis, Dimitrios Galanis, Katerina Gkirtzou, Penny Labropoulou, Kalina Bontcheva (+24 others)
2020 Zenodo  
The ELG is a scalable cloud platform, providing, in an easy-to-integrate way, access to hundreds of commercial and non-commercial LTs for all European languages, including running tools and services as  ...  The European Language Grid (ELG) project addresses this fragmentation by establishing the ELG as the primary platform for LT in Europe.  ...  It orchestrates service execution by calling the LT service, also handling failures, timeouts etc.  ... 
doi:10.5281/zenodo.4058239 fatcat:5akfvrtitzdpneqsz4osusgvzi

A Comparison of Knowledge Extraction Tools for the Semantic Web [chapter]

Aldo Gangemi
2013 Lecture Notes in Computer Science  
In the last years, basic NLP tasks: NER, WSD, relation extraction, etc. have been configured for Semantic Web tasks including ontology learning, linked data population, entity resolution, NL querying to  ...  In this paper we describe a landscape analysis of several tools, either conceived specifically for KE on the Semantic Web, or adaptable to it, or even acting as aggregators of extracted data from other  ...  Despite recent uprise in adoption of NLP techniques for SW and conversely of SW knowledge for NLP, there is still a large gap between the data structures of lexical and NLP data, and the formal semantics  ... 
doi:10.1007/978-3-642-38288-8_24 fatcat:fgosgv2nyncnhdyqexolmtp5su

Masking Orchestration: Multi-Task Pretraining for Multi-Role Dialogue Representation Learning

Tianyi Wang, Yating Zhang, Xiaozhong Liu, Changlong Sun, Qiong Zhang
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Meanwhile, in order to locate essential information for dialogue summarization/extraction, the pretraining process enables external knowledge integration.  ...  While dialogue corpora are abundantly available, labeled data, for specific learning tasks, can be highly scarce and expensive.  ...  Model CDD: CFG EMD: DS rouge-1 rouge-2 rouge-3 rouge-L bleu4 rouge-1 rouge-2 rouge-3 rouge-L bleu4 DAHS2S ( customer service for coping with a variety of disputes, however in relatively close legal domain  ... 
doi:10.1609/aaai.v34i05.6459 fatcat:hc7m2juw5jad7f2tihbkcmhhnq
« Previous Showing results 1 — 15 out of 256 results