Dimitrios Galanis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Dimitrios Galanis has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Ion Androutsopoulos
Department of Informatics Athens University of Economics and Business Greece
4 shared publications - Odysseas S. Chlapanis
Department of Informatics Athens University of Economics and Business Greece
4 shared publications - Penny Labropoulou
Institute for Language and Speech Processing, R. C
4 shared publications - Stelios Piperidis
R. C. “Athena
4 shared publications - Athanasia Kolovou
ILSP / Athena RC, Greece
3 shared publications - Ian Roberts
University of Sheffield
3 shared publications
Latest Publications
- Open Access
LAR-ECHR: A New Legal Argument Reasoning Task and Dataset for Cases of the European Court of Human Rights
We present Legal Argument Reasoning (LAR), a novel task designed to evaluate the legal reasoning capabilities of Large Language Models (LLMs). The task requires selecting the correct next statement (from multiple choice options) in a chain of legal arguments from court proceedings, given the facts of the case. We constructed a dataset (LAR-ECHR) for this task using cases from the European Court of Human Rights (ECHR). We evaluated seven general-purpose LLMs on LAR-ECHR and found that (a) the ranking of the models is aligned with that of LegalBench, an established US-based legal reasoning benchmark, even though LAR-ECHR is based on EU law, (b) LAR-ECHR distinguishes top models more clearly, compared to LegalBench, (c) even the best model (GPT-4o) obtains 75.8% accuracy on LAR-ECHR, indicating significant potential for further model improvement. The process followed to construct LAR-ECHR can be replicated with cases from other legal systems.
Open AccessLAR-ECHR: A New Legal Argument Reasoning Task and Dataset for Cases of the European Court of Human Rights
We present Legal Argument Reasoning (LAR), a novel task designed to evaluate the legal reasoning capabilities of Large Language Models (LLMs). The task requires selecting the correct next statement (from multiple choice options) in a chain of legal arguments from court proceedings, given the facts of the case. We constructed a dataset (LAR-ECHR) for this task using cases from the European Court of Human Rights (ECHR). We evaluated seven general-purpose LLMs on LAR-ECHR and found that (a) the ranking of the models is aligned with that of LegalBench, an established US-based legal reasoning benchmark, even though LAR-ECHR is based on EU law, (b) LAR-ECHR distinguishes top models more clearly, compared to LegalBench, (c) even the best model (GPT-4o) obtains 75.8% accuracy on LAR-ECHR, indicating significant potential for further model improvement. The process followed to construct LAR-ECHR can be replicated with cases from other legal systems.
- Open Access
- 9 July 2024
- Published by Linkoping University Electronic Press in Swedish Aerospace Conference, FT2025
The CLARIN:EL infrastructure: Platform, Portal, K-Centre
This paper presents the CLARIN:EL infrastructure, which comprises three pillars: the language resources and technologies Platform, the Portal and the Knowledge Centre. It serves as a com-prehensive and interoperable environment that supports language-related research in the fields of language technology, language studies, digital humanities, and political and social sciences. The Platform facilitates deposition, curation and sharing of digital language resources (catering for providers’ needs), and access to and automatic processing of these resources (catering for con-sumers’ needs). The Portal offers informative material about CLARIN:EL and support services to the community, including dissemination, awareness raising and training activities. The Knowledge Centre promotes digital literacy in the scientific domains served, by providing infor-mation on studies, educational and training material and publications. This paper discusses the CLARIN:EL pillars, the technical architecture, its design and implementation principles, the functionalities offered to the users, the support activities provided, usage analytics and future steps.
- 9 July 2024
- Published by Linkoping University Electronic Press in Swedish Aerospace Conference, FT2025
Open AccessThe CLARIN:EL infrastructure: Platform, Portal, K-Centre
This paper presents the CLARIN:EL infrastructure, which comprises three pillars: the language resources and technologies Platform, the Portal and the Knowledge Centre. It serves as a com-prehensive and interoperable environment that supports language-related research in the fields of language technology, language studies, digital humanities, and political and social sciences. The Platform facilitates deposition, curation and sharing of digital language resources (catering for providers’ needs), and access to and automatic processing of these resources (catering for con-sumers’ needs). The Portal offers informative material about CLARIN:EL and support services to the community, including dissemination, awareness raising and training activities. The Knowledge Centre promotes digital literacy in the scientific domains served, by providing infor-mation on studies, educational and training material and publications. This paper discusses the CLARIN:EL pillars, the technical architecture, its design and implementation principles, the functionalities offered to the users, the support activities provided, usage analytics and future steps.
- Open Access
Archimedes-AUEB at SemEval-2024 Task 5: LLM explains Civil Procedure
The SemEval task on Argument Reasoning in Civil Procedure is challenging in that it requires understanding legal concepts and inferring complex arguments. Currently, most Large Language Models (LLM) excelling in the legal realm are principally purposed for classification tasks, hence their reasoning rationale is subject to contention. The approach we advocate involves using a powerful teacher-LLM (ChatGPT) to extend the training dataset with explanations and generate synthetic data. The resulting data are then leveraged to fine-tune a small student-LLM. Contrary to previous work, our explanations are not directly derived from the teacher's internal knowledge. Instead they are grounded in authentic human analyses, therefore delivering a superior reasoning signal. Additionally, a new `mutation' method generates artificial data instances inspired from existing ones. We are publicly releasing the explanations as an extension to the original dataset, along with the synthetic dataset and the prompts that were used to generate both. Our system ranked 15th in the SemEval competition. It outperforms its own teacher and can produce explanations aligned with the original human analyses, as verified by legal experts.
Open AccessArchimedes-AUEB at SemEval-2024 Task 5: LLM explains Civil Procedure
The SemEval task on Argument Reasoning in Civil Procedure is challenging in that it requires understanding legal concepts and inferring complex arguments. Currently, most Large Language Models (LLM) excelling in the legal realm are principally purposed for classification tasks, hence their reasoning rationale is subject to contention. The approach we advocate involves using a powerful teacher-LLM (ChatGPT) to extend the training dataset with explanations and generate synthetic data. The resulting data are then leveraged to fine-tune a small student-LLM. Contrary to previous work, our explanations are not directly derived from the teacher's internal knowledge. Instead they are grounded in authentic human analyses, therefore delivering a superior reasoning signal. Additionally, a new `mutation' method generates artificial data instances inspired from existing ones. We are publicly releasing the explanations as an extension to the original dataset, along with the synthetic dataset and the prompts that were used to generate both. Our system ranked 15th in the SemEval competition. It outperforms its own teacher and can produce explanations aligned with the original human analyses, as verified by legal experts.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 267-279
LAR-ECHR: A New Legal Argument Reasoning Task and Dataset for Cases of the European Court of Human Rights
Odysseas Chlapanis, Dimitris Galanis, Ion Androutsopoulos. Proceedings of the Natural Legal Language Processing Workshop 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 267-279
Open AccessLAR-ECHR: A New Legal Argument Reasoning Task and Dataset for Cases of the European Court of Human Rights
Odysseas Chlapanis, Dimitris Galanis, Ion Androutsopoulos. Proceedings of the Natural Legal Language Processing Workshop 2024. 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 1607-1622
Archimedes-AUEB at SemEval-2024 Task 5: LLM explains Civil Procedure
Odysseas Chlapanis, Ion Androutsopoulos, Dimitrios Galanis. Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 1607-1622
Open AccessArchimedes-AUEB at SemEval-2024 Task 5: LLM explains Civil Procedure
Odysseas Chlapanis, Ion Androutsopoulos, Dimitrios Galanis. Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024). 2024.
- Open Access
- 2 November 2022
- Published by Springer Nature
- p. 67-93
Contributing to the European Language Grid as a Provider
The ELG platform enables producers of language resources and language technology tools and services to upload, describe, share, and distribute their services and products as well as to describe their companies, academic organisations and projects. This chapter presents the functionalities offered through web-based user interfaces for describing LT resources or related entities with metadata and for managing their publication. It gives a detailed description of the options that providers of LT tools can exploit to integrate them into ELG as ready-to-deploy services and the tools that ELG offers in their support during the preparation, upload and integration phases. The tools and packaging recommendations for resources to be uploaded in ELG are also presented. The chapter concludes with a discussion of functionalities offered to providers by ELG and other related platforms.
- 2 November 2022
- Published by Springer Nature
- p. 67-93
Open AccessContributing to the European Language Grid as a Provider
The ELG platform enables producers of language resources and language technology tools and services to upload, describe, share, and distribute their services and products as well as to describe their companies, academic organisations and projects. This chapter presents the functionalities offered through web-based user interfaces for describing LT resources or related entities with metadata and for managing their publication. It gives a detailed description of the options that providers of LT tools can exploit to integrate them into ELG as ready-to-deploy services and the tools that ELG offers in their support during the preparation, upload and integration phases. The tools and packaging recommendations for resources to be uploaded in ELG are also presented. The chapter concludes with a discussion of functionalities offered to providers by ELG and other related platforms.
- Open Access
- 2 November 2022
- Published by Springer Nature
- p. 131-149
Language Technology Tools and Services
At the time of writing, the European Language Grid includes more than 800 LT services of varied types, including machine translation (MT), automatic speech recognition (ASR), text-to-speech synthesis (TTS), and text analysis ranging from simple tokenisers and part-of-speech taggers through to complete named entity recognition and sentiment analysis systems. This chapter gives a high-level summary of the development of the ELG service catalogue over time and digs deeper to discuss the process of service integration by looking at a few example services.
- 2 November 2022
- Published by Springer Nature
- p. 131-149
Open AccessLanguage Technology Tools and Services
At the time of writing, the European Language Grid includes more than 800 LT services of varied types, including machine translation (MT), automatic speech recognition (ASR), text-to-speech synthesis (TTS), and text analysis ranging from simple tokenisers and part-of-speech taggers through to complete named entity recognition and sentiment analysis systems. This chapter gives a high-level summary of the development of the ELG service catalogue over time and digs deeper to discuss the process of service integration by looking at a few example services.
- Open Access
- 2 November 2022
- Published by Springer Nature
- p. 37-66
Using the European Language Grid as a Consumer
This chapter describes the European Language Grid cloud platform from the point of view of a consumer who wishes to access language resources or make use of language technology tools and services. Three aspects are discussed: 1. the webbased user interface (UI) for casual and non-technical users, 2. the underlying REST APIs that drive the UI but can also be called directly by third parties to integrate ELG functionality in their own tools, and 3. the Python Software Development Kit (SDK) that we have developed to simplify access to these APIs from Python code. The chapter concludes with a preview of the upcoming payment module that will enable the sale of commercial LT services and resources through ELG, and a discussion of how ELG compares and relates to other similar platforms and initiatives.
- 2 November 2022
- Published by Springer Nature
- p. 37-66
Open AccessUsing the European Language Grid as a Consumer
This chapter describes the European Language Grid cloud platform from the point of view of a consumer who wishes to access language resources or make use of language technology tools and services. Three aspects are discussed: 1. the webbased user interface (UI) for casual and non-technical users, 2. the underlying REST APIs that drive the UI but can also be called directly by third parties to integrate ELG functionality in their own tools, and 3. the Python Software Development Kit (SDK) that we have developed to simplify access to these APIs from Python code. The chapter concludes with a preview of the upcoming payment module that will enable the sale of commercial LT services and resources through ELG, and a discussion of how ELG compares and relates to other similar platforms and initiatives.
- Open Access
- 2 November 2022
- Published by Springer Nature
- p. 13-36
The European Language Grid Platform:Basic Concepts
In the fragmented Language Technology (LT) landscape of multilingual Europe, ELG has set out to bring together language resources and technologies (LRTs) and boost the LT sector and its activities. The primary goal is to build a scalable and comprehensive cloud platform for providers, developers, integrators and consumers of language resources and technologies. We describe the basic concepts of the ELG platform in terms of its architecture, the functionalities and services offered to its types of users and the policies it implements. We present the ELG repository, its catalogue features, the LT services execution environment as well as the metadata model underlying the platform operations and the resources life cycle, from creation to publication. We also discuss the compliance of ELG with the FAIR principles and the relation to other platforms and infrastructure initiatives which have inspired certain aspects and with which ELG has been establishing strong links.
- 2 November 2022
- Published by Springer Nature
- p. 13-36
Open AccessThe European Language Grid Platform:Basic Concepts
In the fragmented Language Technology (LT) landscape of multilingual Europe, ELG has set out to bring together language resources and technologies (LRTs) and boost the LT sector and its activities. The primary goal is to build a scalable and comprehensive cloud platform for providers, developers, integrators and consumers of language resources and technologies. We describe the basic concepts of the ELG platform in terms of its architecture, the functionalities and services offered to its types of users and the policies it implements. We present the ELG repository, its catalogue features, the LT services execution environment as well as the metadata model underlying the platform operations and the resources life cycle, from creation to publication. We also discuss the compliance of ELG with the FAIR principles and the relation to other platforms and infrastructure initiatives which have inspired certain aspects and with which ELG has been establishing strong links.