1 code implementation • EMNLP (NLLP) 2021 • Ingo Glaser, Sebastian Moser, Florian Matthes
In this paper, we propose the task of automatic summarization of German court rulings.
no code implementations • NAACL (PrivateNLP) 2022 • Oleksandra Klymenko, Stephen Meisenbacher, Florian Matthes
As the tide of Big Data continues to influence the landscape of Natural Language Processing (NLP), the utilization of modern NLP methods has grounded itself in this data, in order to tackle a variety of text-based tasks.
no code implementations • ECNLP (ACL) 2022 • Daniel Braun, Florian Matthes
So-called standard form contracts, i. e. contracts that are drafted unilaterally by one party, like terms and conditions of online shops or terms of services of social networks, are cornerstones of our modern economy.
1 code implementation • ECNLP (ACL) 2022 • Tobias Schamel, Daniel Braun, Florian Matthes
While content extraction, in general, is a well-researched field and many open source libraries are available, our evaluation shows, that existing solutions cannot extract Terms and Conditions in sufficient quality, mainly because of their special structure.
2 code implementations • GermEval 2022 • Juraj Vladika, Stephen Meisenbacher, Florian Matthes
The task of quantifying the complexity of written language presents an interesting endeavor, particularly in the opportunity that it presents for aiding language learners.
no code implementations • ACL (NLP4PosImpact) 2021 • Daniel Braun, Florian Matthes
Government and non-government organisations (NGOs) for consumer protection battle such terms on behalf of consumers, who often hesitate to take on legal actions themselves.
no code implementations • 29 Apr 2024 • Juraj Vladika, Stephen Meisenbacher, Martina Preis, Alexandra Klymenko, Florian Matthes
In recent years, the field of Legal Tech has risen in prevalence, as the Natural Language Processing (NLP) and legal disciplines have combined forces to digitalize legal processes.
1 code implementation • 12 Apr 2024 • Juraj Vladika, Florian Matthes
In today's digital world, seeking answers to health questions on the Internet is a common practice.
1 code implementation • 4 Apr 2024 • Stephen Meisenbacher, Nihildev Nandakumar, Alexandra Klymenko, Florian Matthes
The application of Differential Privacy to Natural Language Processing techniques has emerged in relevance in recent years, with an increasing number of studies published in established NLP outlets.
no code implementations • 1 Apr 2024 • Phillip Schneider, Tim Schopf, Juraj Vladika, Florian Matthes
Knowledge management is a critical challenge for enterprises in today's digital world, as the volume and complexity of data being generated and collected continue to grow incessantly.
no code implementations • 5 Feb 2024 • Juraj Vladika, Florian Matthes
We test the final verdict prediction of systems on four datasets of biomedical and health claims in different settings.
1 code implementation • 2 Feb 2024 • Phillip Schneider, Manuel Klettner, Elena Simperl, Florian Matthes
In this study, we conduct an empirical analysis of conversational large language models in generating natural language text from semantic triples.
1 code implementation • 3 Jan 2024 • Phillip Schneider, Manuel Klettner, Kristiina Jokinen, Elena Simperl, Florian Matthes
Conversational question answering systems often rely on semantic parsing to enable interactive information retrieval, which involves the generation of structured database queries from a natural language input.
no code implementations • 21 Dec 2023 • Juraj Vladika, Alexander Fichtl, Florian Matthes
In this paper, we develop an approach that uses lightweight adapter modules to inject structured biomedical knowledge into pre-trained language models (PLMs).
1 code implementation • 8 Oct 2023 • Phillip Schneider, Nils Rehtanz, Kristiina Jokinen, Florian Matthes
Exploratory search is an open-ended information retrieval process that aims at discovering knowledge about a topic or domain rather than searching for a specific answer or piece of information.
1 code implementation • 15 Sep 2023 • Juraj Vladika, Phillip Schneider, Florian Matthes
In the digital age, seeking health advice on the Internet has become a common practice.
no code implementations • 3 Aug 2023 • Tobias Müller, Maximilian Stäbler, Hugo Gascón, Frank Köster, Florian Matthes
Machine Learning (ML) has shown significant potential in various applications; however, its adoption in privacy-critical domains has been limited due to concerns about data privacy.
1 code implementation • 20 Jul 2023 • Tim Schopf, Karim Arabi, Florian Matthes
As an efficient approach to understand, generate, and process natural language texts, research in natural language processing (NLP) has exhibited a rapid spread and wide adoption in recent years.
no code implementations • 15 Jul 2023 • Tim Schopf, Emanuel Gerber, Malte Ostendorff, Florian Matthes
Generic sentence embeddings provide a coarse-grained approximation of semantic textual similarity but ignore specific aspects that make texts similar.
no code implementations • 6 Jul 2023 • Tim Schopf, Dennis N. Schneider, Florian Matthes
Instead, we only train a small number of additional parameters while keeping the weights of the underlying sentence embedding model fixed.
no code implementations • 3 Jul 2023 • Anum Afzal, Juraj Vladika, Daniel Braun, Florian Matthes
Large Language Models work quite well with general-purpose data and many tasks in Natural Language Processing.
no code implementations • 26 May 2023 • Juraj Vladika, Florian Matthes
In particular, scientific fact-checking is the variation of the task concerned with verifying claims rooted in scientific knowledge.
no code implementations • 26 Apr 2023 • Tobias Müller, Milena Zahn, Florian Matthes
This research investigates the challenges of prevailing collaborative business models and distinct aspects of Federated Machine Learning.
1 code implementation • 25 Apr 2023 • Juraj Vladika, Florian Matthes
The first one is a pipeline system that models the two tasks separately, while the second one is a joint system that learns the two tasks simultaneously with a shared representation and a multi-task learning approach.
no code implementations • 24 Mar 2023 • Phillip Schneider, Nils Rehtanz, Kristiina Jokinen, Florian Matthes
By leveraging graph databases to semantically structure news data and implementing an intuitive voice-based interface, our system can help care-dependent people to easily discover relevant news articles and give personalized recommendations.
1 code implementation • 10 Jan 2023 • Phillip Schneider, Anum Afzal, Juraj Vladika, Daniel Braun, Florian Matthes
Conversational search has evolved as a new information retrieval paradigm, marking a shift from traditional search systems towards interactive dialogues with intelligent search agents.
2 code implementations • 29 Nov 2022 • Tim Schopf, Daniel Braun, Florian Matthes
Text classification of unseen classes is a challenging Natural Language Processing task and is mainly attempted using two different types of approaches.
Ranked #1 on Unsupervised Text Classification on AG News (F1-score metric)
no code implementations • 20 Nov 2022 • Phillip Schneider, Markus Voggenreiter, Abdullah Gulraiz, Florian Matthes
Over the last years, software development in domains with high security demands transitioned from traditional methodologies to uniting modern approaches from software development and operations (DevOps).
1 code implementation • 12 Oct 2022 • Tim Schopf, Daniel Braun, Florian Matthes
When successively retrieving documents on different predefined topics from publicly available and commonly used datasets, we achieved an average area under the receiver operating characteristic curve value of 0. 95 on one dataset and 0. 92 on another.
Ranked #1 on Unsupervised Text Classification on AG News
1 code implementation • 11 Oct 2022 • Tim Schopf, Simon Klimek, Florian Matthes
Keyphrase extraction is the process of automatically selecting a small set of most relevant phrases from a given text.
Ranked #2 on Keyphrase Extraction on Inspec
1 code implementation • 30 Sep 2022 • Phillip Schneider, Tim Schopf, Juraj Vladika, Mikhail Galkin, Elena Simperl, Florian Matthes
In pace with developments in the research field of artificial intelligence, knowledge graphs (KGs) have attracted a surge of interest from both academia and industry.
no code implementations • 17 Aug 2022 • Oleksandra Klymenko, Stephen Meisenbacher, Florian Matthes
As such, the question of privacy in NLP has gained fervor in recent years, coinciding with the development of new Privacy-Enhancing Technologies (PETs).
1 code implementation • 6 Apr 2021 • Ahmed Elnaggar, Wei Ding, Llion Jones, Tom Gibbs, Tamas Feher, Christoph Angerer, Silvia Severini, Florian Matthes, Burkhard Rost
Simultaneously, the transformer model, especially its combination with transfer learning, has been proven to be a powerful technique for natural language processing tasks.
1 code implementation • LREC 2020 • Kira Klimt, Daniel Braun, Daniela Schneider, Florian Matthes
Language resources for languages other than English are often scarce.
1 code implementation • WS 2019 • Daniel Braun, Kira Klimt, Daniela Schneider, Florian Matthes
SimpleNLG is a popular open source surface realiser for the English language.
no code implementations • 16 Oct 2018 • Ahmed Elnaggar, Christoph Gebendorfer, Ingo Glaser, Florian Matthes
A potential solution to this problem is multi-task DL to enable transfer learning.
no code implementations • 15 Oct 2018 • Ahmed Elnaggar, Bernhard Waltl, Ingo Glaser, Jörg Landthaler, Elena Scepankova, Florian Matthes
Deep learning methods are often difficult to apply in the legal domain due to the large amount of labeled data required by deep learning methods.
no code implementations • 15 Oct 2018 • Ahmed Elnaggar, Robin Otto, Florian Matthes
However, this paper focuses especially on the aspect of applying transfer learning approach using networks trained for NEL to legal documents.
no code implementations • WS 2017 • Daniel Braun, Elena Scepankova, Patrick Holl, Florian Matthes
Every time we buy something online, we are confronted with Terms of Services.
1 code implementation • WS 2017 • Daniel Braun, Hern, Adrian ez Mendez, Florian Matthes, Manfred Langen
Conversational interfaces recently gained a lot of attention.