A dataset and annotation tool to support the development of German-language Tabular Question Answering systems, with a specific focus on sustainability-related information, exclusive use of the German language and a strong emphasis on information retrieval from tables embedded in sustainability reports.
It is asserted that the present contribution consists of an interpretable domain palette, a constructed benchmark of diverse tabular datasets, and reproducible code and data to enable further research on domain discovery and domain-aware tooling for tabular data.
A novel benchmark framework for linguistic QA retrieval, empirical evidence supporting monolingual IR-specialised models, and insights into retrieval robustness under paraphrastic variation are included, enabling improved QA systems for specialised and low-resource environments.
Pedro Moura, Inês Gama, F. Batista et al.· 0 citations
This paper introduces the task of identifying and segmenting legal conditions (Tatbestand) and legal consequences (Rechtsfolge) within German statutory texts and presents ANNOTARES (Annotations of Tatbestand-Rechtsfolge Sequences), a novel dataset comprising German law texts with span-level annotations.
The extraction of structured information from unstructured documents represents a critical component of digital transformations in all sectors. While proprietary solutions dominate commercial applications, a rapidly growing ecosystem of open-source Optical Character Recognition (OCR) engines, Large Language Models (LLM...
ReTaT is a dataset that can be used to train and evaluate systems for extracting relations whose expression spans the two modalities and its quality and suitability were assessed for the joint table-text relation extraction task using Large Language Models (LLMs).
Mohamed Ettaleb, Thibault Ehrhart, Nathalie Aussenac-Gilles et al.· International Conference on...· 1 citation
By evaluating paper retrieval, evidence grounding, and answer accuracy separately, LitTraceQA provides a testbed for scientific QA systems that produce verifiable answers rather than unsupported summaries.
Xuye Liu, Yimu Wang, Peng Shi et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
