A knowledge-based approach to Information Extraction for semantic interoperability in the archaeology domain
- Submitting institution
-
University of South Wales / Prifysgol De Cymru
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1454647
- Type
- D - Journal article
- DOI
-
10.1002/asi.23485
- Title of journal
- Journal of the Association for Information Science and Technology
- Article number
- -
- First page
- 1138
- Volume
- 67
- Issue
- 5
- ISSN
- 2330-1635
- Open access status
- Out of scope for open access requirements
- Month of publication
- March
- Year of publication
- 2015
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
B - Hypermedia
- Citation count
- 8
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Paper cites a 2012 pilot investigation of a simple prototype returned in REF2014 (https://doi.org/10.1504/IJMSO.2012.050183). This 2016 paper discusses the results of the final system which involved significant further implementation developments and corpus analysis. These include ontology-based relation extraction via syntactical pattern matching based on a custom archaeological corpus, thesaurus informed semantic expansion, significantly enhanced negation detection, various disambiguation techniques. The limited pilot terminology resources were substantially expanded, including the linking of technical glossaries to more general archaeological thesauri. A new systematic gold standard evaluation by experts compares the contribution of the new components in NER and RE performance.____
____Reports on the systematic evaluation of various knowledge based NLP components in archaeological information extraction, including semantic expansion via different thesaurus relationships and an expert gold standard NLP evaluation using the influential (ISO standard) CIDOC-CRM ontology. Detailed 2015 analysis of negation detection (doi 10.1108/PROG-10-2014-0076) was selected as the Outstanding Paper in the 2016 Emerald Literati Network Awards for Excellence. Conducted in collaboration with English Heritage and Archaeology Data Service. Outcomes and techniques informed USW’s NLP contributions to FP7 ARIADNE European archaeology research infrastructure project and subsequent European Open Science Cloud for Research TEXTCROWD Pilot Project (Italian archaeological NER).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -