Papers by Julian Moreno-Schneider

6 papers
A Dataset of German Legal Documents for Named Entity Recognition (2020.lrec-1)

Copied to clipboard

Challenge: a dataset developed for Named Entity Recognition in German federal court decisions is available under a CC-BY 4.0 license.
Approach: They describe a dataset developed for Named Entity Recognition in German federal court decisions.
Outcome: The proposed dataset was developed for training an NER service for German legal documents in the EU project Lynx.
Automatic and Manual Web Annotations in an Infrastructure to handle Fake News and other Online Media Phenomena (L18-1)

Copied to clipboard

Challenge: a growing number of people consume news online, but there are different types of "fake news" many online news outlets use the same journalistic principles that have been in use for newspapers for decades, especially factchecking.
Approach: They propose a metadata scheme to enable users to handle "fake news" they also propose 'filter bubble' effect and abuse language .
Outcome: The proposed metadata scheme enables standardisation of these phenomena in online media.
Orchestrating NLP Services for the Legal Domain (2020.lrec-1)

Copied to clipboard

Challenge: a legal technology system under development in the EU is based on semantic services and a multilingual legal knowledge Graph.
Approach: They propose a workflow manager that enables flexible orchestration of workflows . they describe different use cases and propose prototypical solutions .
Outcome: The proposed system is based on a set of natural language processing and document curation services and a multilingual legal knowledge graph that contains semantic information and meaningful references to legal documents.
Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling (2020.lrec-1)

Copied to clipboard

Challenge: Abstractive summarization is an NLP task with many real-world applications.
Approach: They propose to use a pre-trained language model to train a Transformer-based neural model . they propose a new method of BERT-windowing to allow chunk-wise processing of texts longer than the BERT window size .
Outcome: The proposed model outperforms baseline models on CNN/Daily Mail dataset and shows its superiority on German dataset.
European Language Grid: One Year after (2024.lrec-main)

Copied to clipboard

Challenge: The European Language Grid (ELG) is a cloud platform for the whole European Language Technology community.
Approach: The article provides an overview of the current state of ELG in terms of user adoption and number of language resources and technologies available in early 2024.
Outcome: The European Language Grid (ELG) is a cloud platform for the whole European Language Technology community.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations