BB-GeoGPT: A framework for learning a large language model for geographic information science

Y Zhang, Z Wang, Z He, J Li, G Mai, J Lin, C Wei… - Information Processing …, 2024 - Elsevier
Large language models (LLMs) exhibit impressive capabilities across diverse tasks in
natural language processing. Nevertheless, challenges arise such as large model …

Citation recommendation: approaches and datasets

M Färber, A Jatowt - International Journal on Digital Libraries, 2020 - Springer
Citation recommendation describes the task of recommending citations for a given text. Due
to the overload of published scientific works in recent years on the one hand, and the need …

Generative AI for culturally responsive science assessment: A conceptual framework

M Nyaaba, X Zhai, MZ Faison - Education Sciences, 2024 - search.proquest.com
In diverse classrooms, one of the challenges educators face is creating assessments that
reflect the different cultural backgrounds of every student. This study presents a novel …

Automated retrieval of att&ck tactics and techniques for cyber threat reports

V Legoy, M Caselli, C Seifert, A Peter - arxiv preprint arxiv:2004.14322, 2020 - arxiv.org
Over the last years, threat intelligence sharing has steadily grown, leading cybersecurity
professionals to access increasingly larger amounts of heterogeneous data. Among those …

Visual detection with context for document layout analysis

C Soto, S Yoo - Proceedings of the 2019 Conference on Empirical …, 2019 - aclanthology.org
We present 1) a work in progress method to visually segment key regions of scientific
articles using an object detection technique augmented with contextual features, and 2) a …

[HTML][HTML] Extraction of dimension requirements from engineering drawings for supporting quality control in production processes

B Scheibel, J Mangler, S Rinderle-Ma - Computers in Industry, 2021 - Elsevier
Engineering drawings accompany a workpiece throughout its production process and
include information about the dimensions and tolerances as well as the associated …

PDFDataExtractor: A tool for reading scientific text and interpreting metadata from the typeset literature in the portable document format

M Zhu, JM Cole - Journal of Chemical Information and Modeling, 2022 - ACS Publications
The layout of portable document format (PDF) files is constant to any screen, and the
metadata therein are latent, compared to mark-up languages such as HTML and XML. No …

unarxive: a large scholarly data set with publications' full-text, annotated in-text citations, and links to metadata

T Saier, M Färber - Scientometrics, 2020 - Springer
In recent years, scholarly data sets have been used for various purposes, such as paper
recommendation, citation recommendation, citation context analysis, and citation context …

zbMATH Open: API solutions and research challenges

M Petrera, D Trautwein, I Beckenbach, D Ehsani… - arxiv preprint arxiv …, 2021 - arxiv.org
We present zbMATH Open, the most comprehensive collection of reviews and bibliographic
metadata of scholarly literature in mathematics. Besides our website https://zbMATH. org …

[HTML][HTML] Continuous document layout analysis: Human-in-the-loop AI-based data curation, database, and evaluation in the domain of public affairs

A Peña, A Morales, J Fierrez, J Ortega-Garcia, I Puente… - Information …, 2024 - Elsevier
In the digital era, the amount of digital documents generated each day have being
increasing exponentially with the years, to a point where it is unfeasible to process them …