Context-Compatible Information Fusion for Scientific Knowledge Graphs

Kroll, Hermann; Kalo, Jan-Christoph; Nagel, Denis; Mennicke, Stephan; Balke, Wolf‐Tilo

doi:10.1007/978-3-030-54956-5_3

Cited by 11 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And having a general decision here, whether something is true or not, remains open. We found another interesting example in the real-world knowledge base DBpedia 10 .…”

Section: Investigating Common Knowledge Basesmentioning

confidence: 94%

“…Implicit Contexts. We proposed using document references as an implicit and practical context model [10]. We suggested to store references to the source documents when harvesting statements from it.…”

Section: Explicit Context Modelsmentioning

confidence: 99%

“…Post-acute COVID-19 syndrome is an entity from the Medical Subject Headings (MeSH) 6 . The system responded with a list of commonly known conditions such as Fatigue (44), Dyspnea (19), Anossmia (10), Cognitive Dysfunction (9) and Headache (7). The number in brackets refers to how many documents share the corresponding variable substitution.…”

Section: Narrative Query Graphs For Covid 19mentioning

confidence: 99%

See 2 more Smart Citations

What a Publication Tells You -- Benefits of Narrative Information Access in Digital Libraries

Kroll,

Plötzky,

Pirklbauer

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Knowledge bases allow effective access paths in digital libraries.Here users can specify their information need as graph patterns for precise searches and structured overviews (by allowing variables in queries). But especially when considering textual sources that contain narrative information, i.e., short stories of interest, harvesting statements from them to construct knowledge bases may be a serious threat to the statements' validity. A piece of information, originally stated in a coherent line of arguments, could be used in a knowledge base query processing without considering its vital context conditions. And this can lead to invalid results. That is why we argue to move towards narrative information access by considering contexts in the query processing step. In this way digital libraries can allow users to query for narrative information and supply them with valid answers. In this paper we define narrative information access, demonstrate its benefits for Covid 19 related questions, and argue on the generalizability for other domains such as political sciences.

show abstract

“…And having a general decision here, whether something is true or not, remains open. We found another interesting example in the real-world knowledge base DBpedia 10 .…”

Section: Investigating Common Knowledge Basesmentioning

confidence: 94%

Section: Explicit Context Modelsmentioning

confidence: 99%

Section: Narrative Query Graphs For Covid 19mentioning

confidence: 99%

See 1 more Smart Citation

What a Publication Tells You -- Benefits of Narrative Information Access in Digital Libraries

Kroll,

Plötzky,

Pirklbauer

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Extraction quality: benchmarks (precision and recall), observations, extraction limitations Usefulness: relevance of statements (e.g., non-obvious statements), domain insights, helpfulness for domain experts, usefulness in applications Information, originally connected in coherent written texts, might be broken into not helpful pieces in the end. For a good example, consider a drug-disease treatment: Here context information like the dose or treatment duration, which could give more information about the statement's validity [11], might get lost. We refer to such information as the context of statements, e.g., the surrounding scope in which a statement is valid.…”

Section: Study Goalsmentioning

confidence: 99%

A Library Perspective on Nearly-Unsupervised Information Extraction Workflows in Digital Libraries

Kroll

Pirklbauer

Plötzky

et al. 2022

Proceedings of the 22nd ACM/IEEE Joint Conference on Digital Libraries

Self Cite

View full text Add to dashboard Cite

Information extraction can support novel and effective access paths for digital libraries. Nevertheless, designing reliable extraction workflows can be cost-intensive in practice. On the one hand, suitable extraction methods rely on domain-specific training data. On the other hand, unsupervised and open extraction methods usually produce not-canonicalized extraction results. This paper tackles the question how digital libraries can handle such extractions and if their quality is sufficient in practice. We focus on unsupervised extraction workflows by analyzing them in case studies in the domains of encyclopedias (Wikipedia), pharmacy and political sciences. We report on opportunities and limitations. Finally we discuss best practices for unsupervised extraction workflows.

show abstract

“…However, integrating different and heterogeneous sources into a single knowledge representation comes with new problems, such as the validity of fused information [22], identifying and canonicalizing pieces of information (entity linkage), and practical extraction problems when mining knowledge from different sources; See [33] for a good overview. A remedy might be the use of narrative information access to bypass the necessary integration of different sources.…”

Section: Introductionmentioning

confidence: 99%

On Dimensions of Plausibility for Narrative Information Access to Digital Libraries

Kroll

Niklas

Balke

2022

Linking Theory and Practice of Digital Libraries

Self Cite

View full text Add to dashboard Cite

Designing keyword-based access paths is a common practice in digital libraries. They are easy to use and accepted by users and come with moderate costs for content providers. However, users usually have to break down the search into pieces if they search for stories of interest that are more complex than searching for a few keywords. After searching for every piece one by one, information must then be reassembled manually. In previous work we recommended narrative information access, i.e., users can precisely state their information needs as graph patterns called narratives. Then a system takes a narrative and searches for evidence for each of its parts. If the whole query, i.e., every part, can be bound against data, the narrative is considered plausible and, thus, the query is answered. But is it as easy as that? In this work we perform case studies to analyze the process of making a given narrative plausible. Therefore, we summarize conceptual problems and challenges to face. Moreover, we contribute a set of dimensions that must be considered when realizing narrative information access in digital libraries.

show abstract

Context-Compatible Information Fusion for Scientific Knowledge Graphs

Cited by 11 publications

References 16 publications

What a Publication Tells You -- Benefits of Narrative Information Access in Digital Libraries

What a Publication Tells You -- Benefits of Narrative Information Access in Digital Libraries

A Library Perspective on Nearly-Unsupervised Information Extraction Workflows in Digital Libraries

On Dimensions of Plausibility for Narrative Information Access to Digital Libraries

Contact Info

Product

Resources

About