We present two multilingual LLMs, Teuken 7B-base and Teuken 7B-instruct, designed to embrace Europe’s linguistic diversity by supporting all 24 official languages of the European Union. Trained on a dataset comprising around 60% non-English data and utilizing a custom multilingual tokenizer, our models address the limitations of existing Large Language Models (LLMs) that predominantly focus on English or a few high-resource languages. We detail the models’ development principles, i.e., data composition, tokenizer optimization, and training methodologies. The models demonstrate strong performance across multilingual benchmarks, as evidenced by their performance on European versions of ARC, HellaSwag, and TruthfulQA.

The steep increase in the number of scholarly publications has given rise to various digital repositories, libraries and knowledge graphs aimed to capture, manage, and preserve scientific data. Efficiently navigating such databases requires a system able to classify scholarly documents according to the respective research (sub-)field. However, not every digital repository possesses a relevant classification schema for categorising publications. For instance, one of the largest digital archives in Computational Linguistics (CL) and Natural Language Processing (NLP), the ACL Anthology, lacks a system for classifying papers into topics and sub-topics. This paper addresses this gap by constructing a corpus of 1,500 ACL Anthology publications annotated with their main contributions using a novel hierarchical taxonomy of core CL/NLP topics and sub-topics. The corpus is used in a shared task with the goal of classifying CL/NLP papers into their respective sub-topics.

We present and describe two language resources in this paper: CATalog 1.0, the largest text corpus in Catalan to date, and CURATE (Corpus Utility for RAting TExt), a modular, parallelizable pipeline used for processing and scoring documents based on text quality that we have optimised to run in High Performance Cluster (HPC) environments. In the coming sections we describe our data preprocessing pipeline at length; traditional pipelines usually implement a set of binary filters such that a given document is either in or out. In our experience with Catalan, in lower-resource settings it is more practical to instead assign a document a soft score to allow for more flexible decision-making. We describe how the document score is calculated and highlight its interpretability by showing that it is significantly correlated with human judgements as obtained from a comparative judgement experiment. We additionally describe the different subcorpora that make up CATalog 1.0.

The Common European Language Data Space (LDS) is an integral part of the EU data strategy, which aims at developing a single market for data. Its decentralised technical infrastructure and governance scheme are currently being developed by the LDS project, which also has dedicated tasks for proof-of-concept prototypes, handling legal aspects, raising awareness and promoting the LDS through events and social media channels. The LDS is part of a broader vision for establishing all necessary components to develop European large language models.

The European Language Grid (ELG) is a cloud platform for the whole European Language Technology community. While the EU project that developed the platform successfully concluded in June 2022, the ELG initiative has continued. This article provides a description of the current state of ELG in terms of user adoption and number of language resources and technologies available in early 2024. It also provides an overview of the various activities with regard to ELG since the end of the project and since the publication of the ELG book, especially the co-authors’ attempt to integrate the ELG platform into various data space initiatives. The article also provides an overview of the Digital Language Equality (DLE) dashboard and the current state of DLE in Europe.

This paper addresses the challenge of integrating low-resource languages into multilingual automatic speech recognition (ASR) systems. We introduce a novel application of weighted cross-entropy, typically used for unbalanced datasets, to facilitate the integration of low-resource languages into pre-trained multilingual ASR models within the context of continual multilingual learning. We fine-tune the Whisper multilingual ASR model on five high-resource languages and one low-resource language, employing language-weighted dynamic cross-entropy and data augmentation. The results show a remarkable 6.69% word error rate (WER) reduction for the low-resource language compared to the fine-tuned model without applying our approach, and a 48.86% WER reduction compared to the original Whisper model. In addition, our approach yields an average WER reduction of 3.29% across the six languages, showing no degradation for the high-resource languages.

This paper provides an overview of the ongoing European Language Equality(ELE) project, an 18-month action funded by the European Commission which involves 52 partners. The primary goal of ELE is to prepare the European Language Equality Programme, in the form of a strategic research, innovation and implementation agenda and a roadmap for achieving full digital language equality (DLE) in Europe by 2030.

Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics.Prior work relies on discrete citation relations to generate contrast samples.However, discrete citations enforce a hard cutoff to similarity.This is counter-intuitive to similarity-based learning and ignores that scientific papers can be very similar despite lacking a direct citation -a core problem of finding related research.Instead, we use controlled nearest neighbor sampling over citation graph embeddings for contrastive learning.This control allows us to learn continuous similarity, to sample hard-to-learn negatives and positives, and also to avoid collisions between negative and positive samples by controlling the sampling margin between them.The resulting method SciNCL outperforms the state-of-theart on the SciDocs benchmark.Furthermore, we demonstrate that it can train (or tune) language models sample-efficiently and that it can be combined with recent training-efficient methods.Perhaps surprisingly, even training a general-domain language model this way outperforms baselines pretrained in-domain.

Almost all summarisation methods and datasets focus on a single language and short summaries. We introduce a new dataset called WikinewsSum for English, German, French, Spanish, Portuguese, Polish, and Italian summarisation tailored for extended summaries of approx. 11 sentences. The dataset comprises 39,626 summaries which are news articles from Wikinews and their sources. We compare three multilingual transformer models on the extractive summarisation task and three training scenarios on which we fine-tune mT5 to perform abstractive summarisation. This results in strong baselines for both extractive and abstractive summarisation on WikinewsSum. We also show how the combination of an extractive model with an abstractive one can be used to create extended abstractive summaries from long input documents. Finally, our results show that fine-tuning mT5 on all the languages combined significantly improves the summarisation performance on low-resource languages.

To cope with the COVID-19 pandemic, many jurisdictions have introduced new or altered existing legislation. Even though these new rules are often communicated to the public in news articles, it remains challenging for laypersons to learn about what is currently allowed or forbidden since news articles typically do not reference underlying laws. We investigate an automated approach to extract legal claims from news articles and to match the claims with their corresponding applicable laws. We examine the feasibility of the two tasks concerning claims about COVID-19-related laws from Berlin, Germany. For both tasks, we create and make publicly available the data sets and report the results of initial experiments. We obtain promising results with Transformer-based models that achieve 46.7 F1 for claim extraction and 91.4 F1 for law matching, albeit with some conceptual limitations. Furthermore, we discuss challenges of current machine learning approaches for legal language processing and their ability for complex legal reasoning tasks.

We present a dataset consisting of German offensive and non-offensive tweets, annotated for speech acts. These 600 tweets are a subset of the dataset by Struß et al. (2019) and comprises three levels of annotation, i.e., six coarse-grained speech acts, 23 fine-grained speech acts and 14 different sentence types. Furthermore, we provide an evaluation in both qualitative and quantitative terms. The dataset is made publicly available under a CC-BY-4.0 license.

Semantic Storytelling describes the goal to automatically and semi-automatically generate stories based on extracted, processed, classified and annotated information from large content resources. Essential is the automated processing of text segments extracted from different content resources by identifying the relevance of a text segment to a topic and its semantic relation to other text segments. In this paper we present an approach to create an automatic classifier for semantic relations between extracted text segments from different news articles. We devise custom annotation guidelines based on various discourse structure theories and annotate a dataset of 2,501 sentence pairs extracted from 2,638 Wikinews articles. For the annotation, we developed a dedicated annotation tool. Based on the constructed dataset, we perform initial experiments with Transformer language models that are trained for the automatic classification of semantic relations. Our results with promising high accuracy scores suggest the validity and applicability of our approach for future Semantic Storytelling solutions.

We present an extension of the SynSemClass Event-type Ontology, originally conceived as a bilingual Czech-English resource. We added German entries to the classes representing the concepts of the ontology. Having a different starting point than the original work (unannotated parallel corpus without links to a valency lexicon and, of course, different existing lexical resources), it was a challenge to adapt the annotation guidelines, the data model and the tools used for the original version. We describe the process and results of working in such a setup. We also show the next steps to adapt the annotation process, data structures and formats and tools necessary to make the addition of a new language in the future more smooth and efficient, and possibly to allow for various teams to work on SynSemClass extensions to many languages concurrently. We also present the latest release which contains the results of adding German, freely available for download as well as for online access.

The EU-funded project Lynx focuses on the creation of a knowledge graph for the legal domain (Legal Knowledge Graph, LKG) and its use for the semantic processing, analysis and enrichment of documents from the legal domain. This article describes the use cases covered in the project, the entire developed platform and the semantic analysis services that operate on the documents.

Passage ordering aims to maximise discourse coherence in document generation or document modification tasks such as summarisation or storytelling. This paper extends the passage ordering task from sentences to paragraphs, i.e., passages with multiple sentences. Increasing the passage length increases the task's difficulty. To account for this, we propose the combination of a pre-trained encoder-decoder Transformer model, namely BART, with variations of pointer networks. We empirically evaluate the proposed models for sentence and paragraph ordering. Our best model outperforms previous state of the art methods by 0.057 Kendall's Tau on one of three sentence ordering benchmarks (arXiv, VIST, ROC-Story). For paragraph ordering, we construct two novel datasets from Wikipedia and CNN-DailyMail on which we achieve 0.67 and 0.47 Kendall's Tau. The best model variation utilises multiple pointer networks in an ensemble-like fashion. We hypothesise that the use of multiple pointers better reflects the multitude of possible orders of paragraphs in more complex texts. Our code, data, and models are publicly available1.

Recommender systems assist legal professionals in finding relevant literature for supporting their case. Despite its importance for the profession, legal applications do not reflect the latest advances in recommender systems and representation learning research. Simultaneously, legal recommender systems are typically evaluated in small-scale user study without any public available benchmark datasets. Thus, these studies have limited reproducibility. To address the gap between research and practice, we explore a set of state-of-the-art document representation methods for the task of retrieving semantically related US case law. We evaluate text-based (e.g., fast-Text, Transformers), citation-based (e.g., DeepWalk, Poincaré), and hybrid methods. We compare in total 27 methods using two silver standards with annotations for 2,964 documents. The silver standards are newly created from Open Case Book and Wikisource and can be reused under an open license facilitating reproducibility. Our experiments show that document representations from averaged fastText word vectors (trained on legal corpora) yield the best results, closely followed by Poincaré citation embeddings. Combining fastText and Poincaré in a hybrid manner further improves the overall result. Besides the overall performance, we analyze the methods depending on document length, citation count, and the coverage of their recommendations.

We work on the creation of a corpus, crawled from the internet, on the Berlin district of Moabit, primarily meant for training NER systems in German and English. Typical NER corpora and corresponding systems distinguish persons, organisations and locations, but do not distinguish different types of location entities. For our tourism-inspired use case, we need fine-grained annotations for toponyms. In this paper, we outline the fine-grained classification of geographical entities, the resulting annotations and we present preliminary results on automatically tagging toponyms in a small, bootstrapped gold corpus.

Traditional document similarity measures provide a coarse-grained distinction between similar and dissimilar documents.Typically, they do not consider in what aspects two documents are similar.This limits the granularity of applications like recommender systems that rely on document similarity.In this paper, we extend similarity with aspect information by performing a pairwise document classification task.We evaluate our aspect-based document similarity approach for research papers.Paper citations indicate the aspect-based similarity, i. e., the title of a section in which a citation occurs acts as a label for the pair of citing and cited paper.We apply a series of Transformer models such as RoBERTa, ELECTRA, XLNet, and BERT variations and compare them to an LSTM baseline.We perform our experiments on two newly constructed datasets of 172,073 research paper pairs from the ACL Anthology and CORD-19 corpus.According to our results, SciBERT is the best performing system with F1-scores of up to 0.83.A qualitative analysis validates our quantitative results and indicates that aspect-based document similarity indeed leads to more fine-grained recommendations.

We explore to what extent knowledge about the pre-trained language model that is used is beneficial for the task of abstractive summarization. To this end, we experiment with conditioning the encoder and decoder of a Transformer-based neural model on the BERT language model. In addition, we propose a new method of BERT-windowing, which allows chunk-wise processing of texts longer than the BERT window size. We also explore how locality modeling, i.e., the explicit restriction of calculations to the local context, can affect the summarization ability of the Transformer. This is done by introducing 2-dimensional convolutional self-attention into the first layers of the encoder. The results of our models are compared to a baseline and the state-of-the-art models on the CNN/Daily Mail dataset. We additionally train our model on the SwissText dataset to demonstrate usability on German. Both models outperform the baseline in ROUGE scores on two datasets and show its superiority in a manual qualitative analysis.

The current scientific and technological landscape is characterised by the increasing availability of data resources and processing tools and services. In this setting, metadata have emerged as a key factor facilitating management, sharing and usage of such digital assets. In this paper we present ELG-SHARE, a rich metadata schema catering for the description of Language Resources and Technologies (processing and generation services and tools, models, corpora, term lists, etc.), as well as related entities (e.g., organizations, projects, supporting documents, etc.). The schema powers the European Language Grid platform that aims to be the primary hub and marketplace for industry-relevant Language Technology in Europe. ELG-SHARE has been based on various metadata schemas, vocabularies, and ontologies, as well as related recommendations and guidelines.

We describe a dataset developed for Named Entity Recognition in German federal court decisions. It consists of approx. 67,000 sentences with over 2 million tokens. The resource contains 54,000 manually annotated entities, mapped to 19 fine-grained semantic classes: person, judge, lawyer, country, city, street, landscape, organization, company, institution, court, brand, law, ordinance, European legal norm, regulation, contract, court decision, and legal literature. The legal documents were, furthermore, automatically annotated with more than 35,000 TimeML-based time expressions. The dataset, which is available under a CC-BY 4.0 license in the CoNNL-2002 format, was developed for training an NER service for German legal documents in the EU project Lynx.

With 24 official EU and many additional languages, multilingualism in Europe and an inclusive Digital Single Market can only be enabled through Language Technologies (LTs). European LT business is dominated by hundreds of SMEs and a few large players. Many are world-class, with technologies that outperform the global players. However, European LT business is also fragmented – by nation states, languages, verticals and sectors, significantly holding back its impact. The European Language Grid (ELG) project addresses this fragmentation by establishing the ELG as the primary platform for LT in Europe. 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 well as data sets and resources. Once fully operational, it will enable the commercial and non-commercial European LT community to deposit and upload their technologies and data sets into the ELG, to deploy them through the grid, and to connect with other resources. The ELG will boost the Multilingual Digital Single Market towards a thriving European LT community, creating new jobs and opportunities. Furthermore, the ELG project organises two open calls for up to 20 pilot projects. It also sets up 32 national competence centres and the European LT Council for outreach and coordination purposes.

Multilingualism is a cultural cornerstone of Europe and firmly anchored in the European treaties including full language equality. However, language barriers impacting business, cross-lingual and cross-cultural communication are still omnipresent. Language Technologies (LTs) are a powerful means to break down these barriers. While the last decade has seen various initiatives that created a multitude of approaches and technologies tailored to Europe’s specific needs, there is still an immense level of fragmentation. At the same time, AI has become an increasingly important concept in the European Information and Communication Technology area. For a few years now, AI – including many opportunities, synergies but also misconceptions – has been overshadowing every other topic. We present an overview of the European LT landscape, describing funding programmes, activities, actions and challenges in the different countries with regard to LT, including the current state of play in industry and the LT market. We present a brief overview of the main LT-related activities on the EU level in the last ten years and develop strategic guidance with regard to four key dimensions.

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.

We present a new corpus comprising annotations of medical entities in case reports, originating from PubMed Central’s open access library. In the case reports, we annotate cases, conditions, findings, factors and negation modifiers. Moreover, where applicable, we annotate relations between these entities. As such, this is the first corpus of this kind made available to the scientific community in English. It enables the initial investigation of automatic information extraction from case reports through tasks like Named Entity Recognition, Relation Extraction and (sentence/paragraph) relevance detection. Additionally, we present four strong baseline systems for the detection of medical entities made available through the annotated dataset.