Call for papers: Special Issue on

Knowledge Graph Generation from Text

This special issue aims to explore the latest research trends and enhance the state-of-the-art in the field of knowledge graph generation from text. It also intends to address the recent advancement of large language models and foundation models and their impact on knowledge graph generation.

Knowledge graphs have emerged as key technologies for representing knowledge in a variety of domains and supporting intelligent applications, such as chatbots, question answering systems, and recommendation systems. Creating knowledge graphs can be an expensive and time-consuming task; thus numerous techniques have been proposed in the past few years to automatically generate them from textual sources in various fields, such as research data (ORKG, CS-KG, Nanopublications), question answering (ParaQA, NSQA), common sense (CSKG), automotive (CoSI, ASKG), biomedical (Hetionet), and many others. However, current solutions still suffer from important limitations regarding accuracy, completeness, privacy, biases, and scalability. Therefore, automatically producing a large-scale knowledge graph from text corpora is still an open challenge.

The special issue shall provide a comprehensive overview of the latest research trend and inspire further research in this exciting and rapidly evolving area. We welcome original research papers that propose novel techniques, models, and frameworks for generating high-quality and reliable knowledge graphs from text data and addressing the aforementioned limitations. We encourage contributions from multiple research fields, including Natural Language Processing (NLP), Entity Linking (EL), Relation Extraction (RE), Knowledge Representation and Reasoning (KRR), Deep Learning (DL), Knowledge Base Construction (KBC), Semantic Web, Linked Data, and Language Models.

Themes and Topics

We are interested in (including but not limited to) the following themes and topics that study the generation of Knowledge Graphs from text, based on quantitative, qualitative, and mixed research methods.

• Approaches for generating Knowledge Graphs from text
• Use of Large Language Models (LLMs) and Foundation Models for Knowledge Graph (KG) generation
• Ontologies for representing provenance/metadata of generated KGs
• Benchmarks for KG generation from text
• Evaluation methods for KGs generated from text
• Complementarity of LLMs and KGs in important applications
• Industrial applications involving KGs generation from text
• Entity and relation extraction
• Entity and relation linking
• Semantic Parsing
• Open Information Extraction
• Fact checking for generated Knowledge Graphs
• Deep Learning and Generative approaches
• Human-in-the-loop methods

Deadline

• Submission deadline: 29 February 2024 (extended!). Papers submitted before the deadline will be reviewed upon receipt.

Author Guidelines

We invite full papers, dataset descriptions, application reports and reports on tools and systems. Submissions must be original and should not have been published previously or be under consideration for publication while being evaluated for this special issue. Authors can extend previously published conference or workshop papers; guidelines for this can be found in FAQ 9

Submissions shall be made through the Semantic Web journal website at http://www.semantic-web-journal.net. Prospective authors must take notice of the submission guidelines posted at http://www.semantic-web-journal.net/authors. We welcome any submission type as described http://www.semantic-web-journal.net/authors#types. While there is no upper limit, paper length must be justified by content.

Note that you need to request an account on the website for submitting a paper. Please indicate in the cover letter that it is for the "Knowedge Graph Generation from Text" special issue. All manuscripts will be reviewed based on the SWJ open and transparent review policy and will be made available online during the review process.

Also note that the Semantic Web journal is open access and all submissions rely on an open and transparent review process (see FAQ 1). Finally please note that submissions must comply with the journal’s Open Science Data requirements, which are detailed in the corresponding blog post.

Guest Editors

The guest editors can be reached at text2kg-swj@googlegroups.com .

Sanju Tiwari, UAT Mexico
Nandana Mihindukulasooriya, MIT-IBM Watson AI Lab, USA
Francesco Osborne, KMi, The Open University
Dimitris Kontokostas, Medidata, Greece
Jennifer D’Souza, TIB, Germany
Mayank Kejriwal, University of Southern California, USA

Guest Editorial Board

Angelo Salatino, The Open University, UK
Antonella Carbonaro, University of Bologna, Italy
Amna Dirdi, Birmingham City University, UK
Davide Buscaldi, Université Paris 13, France
Dimitris Kontokostas, Medidata, Greece
Edgard Marx, Leipzig University of Applied Sciences (HTWK), Germany
Edlira Vakaj, Birmingham City University, UK
Fernando Ortiz-Rodriguez, Universidad Autonoma de Tamaulipas, Mexico
Francesco Osborne, The Open University, UK
Hong Yung (Joey) Yip, University of South Carolina, USA
Hossein Ghomeshi, Birmingham City University, UK
Jennifer D’Souza, TIB, Germany
Joey Yip, University of South Carolina, USA
Mauro Dragoni, FBK, Italy
Maosheng Guo, Diffbot, USA
Mayank Kejriwal, University of Southern California, USA
Nandana Mihindukoolasurya, IBM Research, Ireland
Sanju Tiwari, Universidad Autonoma de Tamaulipas, Mexico
Sarra Ben-Abbes, Engie, Paris
Sven Groppe, Universität zu Lübeck, Germany
Tek Raj Chhetri, University of Innsbruck, Austria
Tomasso Soru, Serendipity AI, UK