Extracting Hierarchical Relations Between the Back-of-the-Book Index Terms

Li, Ning; Tian, Meng; Lv, S. H.

doi:10.1007/978-3-030-38189-9_45

“…They were able to explore how various network types capture distinct aspects of published scholarship thanks to this corpus, which also allowed for systematic analysis and comparison of various citation network types. Furthermore, parsing of digitized indexes was employed for the construction of controlled vocabularies [Piotrowski and Senn, 2012], gazetteers of historical places [Piotrowski, 2010] and literary authors and works [Romanello et al, 2009], for improving access to historical archives , for building character networks from literary texts [Rochat, 2014], and for reconstructing the ontological relations implied by hierarchical relations between index terms [Li et al, 2019].…”

Section: Index Processingmentioning

confidence: 99%

From Books to Knowledge Graphs

Kokash¹,

Romanello²,

Suyver³

et al. 2023

Journal of Data Mining &Amp; Digital Humanities

0

View full text Add to dashboard Cite

The digital transformation of the scientific publishing industry has led to dramatic improvements in content discoverability and information analytics. Unfortunately, these improvements have not been uniform across research areas. The scientific literature in the arts, humanities and social sciences (AHSS) still lags behind, in part due to the scale of analog backlogs, the persisting importance of national languages, and a publisher ecosystem made of many, small or medium enterprises. We propose a bottom-up approach to support publishers in creating and maintaining their own publication knowledge graphs in the open domain. We do so by releasing a pipeline able to extract structured information from the bibliographies and indexes of AHSS publications, disambiguate, normalize and export it as linked data. We test the proposed pipeline on Brill's Classics collection, and release an implementation in open source for further use and improvement.

show abstract

“…Researchers, however, have also recognized the value of existing indexes as sources of structured, human-curated information. The parsing of digitized indexes was employed for the construction of controlled vocabularies [Piotrowski and Senn, 2012], gazetteers of historical places [Piotrowski, 2010] and literary authors and works [Romanello et al, 2009], for improving access to historical archives , for building character networks from literary texts [Rochat, 2014], and for reconstructing the ontological relations implied by hierarchical relations between index terms [Li et al, 2019].…”

Section: Index Processingmentioning

confidence: 99%

From Books to Knowledge Graphs

Kokash¹,

Romanello²,

Suyver³

et al. 2022

Preprint

0

View full text Add to dashboard Cite

The digital transformation of the scientific publishing industry has led to dramatic improvements in content discoverability and information analytics. Unfortunately, these improvements have not been uniform across research areas. The scientific literature in the arts, humanities and social sciences (AHSS) still lags behind, in part due to the scale of analog backlogs, the persisting importance of national languages, and a publisher ecosystem made of many, small or medium enterprises. We propose a bottom-up approach to support publishers in creating and maintaining their own publication knowledge graphs in the open domain. We do so by releasing a pipeline able to extract structured information from the bibliographies and indexes of AHSS publications, disambiguate, normalize and export it as linked data. We test the proposed pipeline on Brill's Classics collection, and release an implementation in open source for further use and improvement.

show abstract

“…IsA relation extraction [29,12] is extracting the subsumption (subClassOf) relation between two classes. Entity type aims to classify an entity into a predefined set of types (concepts), such as person, location and organization without new concept recognition [42,17,40].…”

Section: Isa Relation and Entity Typingmentioning

confidence: 99%

Large-Scale Multi-granular Concept Extraction Based on Machine Reading Comprehension

Yuan

¹

,

Yang

²

,

Liang

³

et al. 2021

The Semantic Web – ISWC 2021

3

0

View full text Add to dashboard Cite

The concepts in knowledge graphs (KGs) enable machines to understand natural language, and thus play an indispensable role in many applications. However, existing KGs have the poor coverage of concepts, especially fine-grained concepts. In order to supply existing KGs with more fine-grained and new concepts, we propose a novel concept extraction framework, namely MRC-CE, to extract large-scale multi-granular concepts from the descriptive texts of entities. Specifically, MRC-CE is built with a machine reading comprehension model based on BERT, which can extract more fine-grained concepts with a pointer network. Furthermore, a random forest and rule-based pruning are also adopted to enhance MRC-CE's precision and recall simultaneously. Our experiments evaluated upon multilingual KGs, i.e., English Probase and Chinese CN-DBpedia, justify MRC-CE's superiority over the state-ofthe-art extraction models in KG completion. Particularly, after running MRC-CE for each entity in CN-DBpedia, more than 7,053,900 new concepts (instanceOf relations) are supplied into the KG. The code and datasets have been released at https://github.com/fcihraeipnusnacwh/MRC-CE.

show abstract

Extracting Hierarchical Relations Between the Back-of-the-Book Index Terms

Cited by 3 publications

References 8 publications

From Books to Knowledge Graphs

From Books to Knowledge Graphs

From Books to Knowledge Graphs

Large-Scale Multi-granular Concept Extraction Based on Machine Reading Comprehension

Contact Info

Product

Resources

About