Table Interpretation and Extraction of Semantic Relationships to Synthesize Digital Documents

Perez-Arriaga, Martha O.; Estrada, Trilce; Abad-Mota, Soraya

doi:10.5220/0006436902230232

Cited by 4 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first approach called Cluster is based on the characteristic table structure of rows and columns. Approaches based on similar observations can be found in literature [12,15,16]. Most scientific publications use either a one-or a two-column publication layout.…”

Section: Localizationmentioning

confidence: 98%

“…It has been trained on the Table-Bank dataset that was also developed within the publication. Perez-Arriaga et al [15] presented a system with the goal 3 https://github.com/tabulapdf/tabula/ of capturing the ontological concept of scientific publications. Through noun phrase analysis, named entities (NE) are found within tables and annotated by querying DBpedia.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

KIETA: Key-insight extraction from scientific tables

2022

View full text Add to dashboard Cite

An important but very time consuming part of the research process is literature review. An already large and nevertheless growing ground set of publications as well as a steadily increasing publication rate continue to worsen the situation. Consequently, automating this task as far as possible is desirable. Experimental results of systems are key-insights of high importance during literature review and usually represented in form of tables. Our pipeline KIETA exploits these tables to contribute to the endeavor of automation by extracting them and their contained knowledge from scientific publications. The pipeline is split into multiple steps to guarantee modularity as well as analyzability, and agnosticim regarding the specific scientific domain up until the knowledge extraction step, which is based upon an ontology. Additionally, a dataset of corresponding articles has been manually annotated with information regarding table and knowledge extraction. Experiments show promising results that signal the possibility of an automated system, while also indicating limits of extracting knowledge from tables without any context.

show abstract

Section: Localizationmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

KIETA: Key-insight extraction from scientific tables

2022

View full text Add to dashboard Cite

show abstract

“…47 The relationships between a table and its context are also extracted and annotated, and to remove disambiguation, the provenance of relationships is preserved. 48 A framework named TABEL, developed by Varish Mulwad, has a module for converting a table to a graphical model to infer the semantics of table header, cells, and their relation to each other. These semantics are used to convert the graphical representation to RDF triples by using knowledge bases along with the author's own defined ontology or any other ontology.…”

Section: Using Ontologiesmentioning

confidence: 99%

Accessibility of Tables in PDF Documents

Fayyaz

Khusro

Ullah

2021

ITAL

View full text Add to dashboard Cite

People access and share information over the web and in other digital environments, including digital libraries, in the form of documents such as books, articles, technical reports, etc. These documents are in a variety of formats, of which the Portable Document Format (PDF) is most widely used because of its emphasis on preserving the layout of the original material. The retrieval of relevant material from these derivative documents is challenging for information retrieval (IR) because the rich semantic structure of these documents is lost. The retrieval of important units such as images, figures, algorithms, mathematical formulas, and tables becomes a challenge. Among these elements, tables are particularly important because they can add value to the resource description, discovery, and accessibility of documents not only on the web but also in libraries if they are made retrievable and presentable to readers. Sighted users comprehend tables for sensemaking using visual cues, but blind and visually impaired users must rely on assistive technologies, including text-to-speech and screen readers, to comprehend tables. However, these technologies do not pay sufficient attention to tables in order to effectively present tables to visually impaired individuals. Therefore, ways must be found to make tables in PDF documents not only retrievable but also comprehensible. Before developing such solutions, it is necessary to review the available assistive technologies, tools, and frameworks for their capabilities, strengths, and limitations from the comprehension perspective of blind and visually impaired people, along with suitable environments like digital libraries. We found no such review article that critically and analytically presents and evaluates these technologies. To fill this gap in the literature, this review paper reports on the current state of the accessibility of PDF documents, digital libraries, assistive technologies, tools, and frameworks that make PDF tables comprehensible and accessible to blind and visually impaired people. The study findings have implications for libraries, information sciences, and information retrieval.

show abstract