A knowledge‐based approach to Information Extraction for semantic interoperability in the archaeology domain

Abstract

The article presents a method for automatic semantic indexing of archaeological grey‐literature reports using empirical (rule‐based) Information Extraction techniques in combination with domain‐specific knowledge organization systems. The semantic annotation system (OPTIMA) performs the tasks of Named Entity Recognition, Relation Extraction, Negation Detection, and Word‐Sense Disambiguation using hand‐crafted rules and terminological resources for associating contextual abstractions with classes of the standard ontology CIDOC Conceptual Reference Model (CRM) for cultural heritage and its archaeological extension, CRM‐EH. Relation Extraction (RE) performance benefits from a syntactic‐based definition of RE patterns derived from domain oriented corpus analysis. The evaluation also shows clear benefit in the use of assistive natural language processing (NLP) modules relating to Word‐Sense Disambiguation, Negation Detection, and Noun Phrase Validation, together with controlled thesaurus expansion. The semantic indexing results demonstrate the capacity of rule‐based Information Extraction techniques to deliver interoperable semantic abstractions (semantic annotations) with respect to the CIDOC CRM and archaeological thesauri. Major contributions include recognition of relevant entities using shallow parsing NLP techniques driven by a complimentary use of ontological and terminological domain resources and empirical derivation of context‐driven RE rules for the recognition of semantic relationships from phrases of unstructured text.

User Requirement Solicitation for an Information Retrieval System Applied to Dutch Grey Literature in the Archaeology Domain

“…This requirement has been well documented in previous work (e.g. Richards, Tudhope & Vlachidis 2015; Van den Dries 2016) and some studies have investigated different applications of text mining from archaeological reports in English (Vlachidis and Tudhope 2016;Amrani, Abajian & Kodratoff 2008;Byrne and Klein 2010;Vlachidis and Tudhope 2015) and Dutch (Paijmans and Brandsen 2010;Vlachidis et al 2017).…”

A study of semantic integration across archaeological data and reports in different languages

“…The design of the pipelines followed a rule-based information extraction approach supported by a controlled vocabulary implemented as a GATE resource, originating from the Getty Art and Architecture Thesaurus. This builds on a previous study of extracting entities and relationships of interest from English language archaeological grey literature [33] . In addition to the new multilingual dimension, the case study followed a wood related focus relevant to dendrochronology analysis, including the broad classes object, sample, (wood) material, date ranges.…”

“…More work is needed on Relation Extraction algorithms that could assert CRM properties between entities. The English language NLP output is based on grammatical patterns for Relation Extraction, building on previous work [33] . These extract contextual relationships between objects and dates or material.…”

SISA—Automatic Indexing System for Scientific Articles: Experiments with Location Heuristics Rules Versus TF-IDF Rules

“…The use of more or less complex controlled vocabularies in automatic indexing is a fact. Some examples, although by no means all, are: Strode (1977), Valle Bracero and Fernández García (1983), Biebricher, et al (1988), Silvester, Genuardi and Klingbiel (1994), Gil-Leiva (1997, Plaunt and Nogard (1998), Aronson et al (2000), Steinberger, Hagman and Scheer 2000, Lukhashevich and Dobrov (2001), Montejo (2001), Zha and Hou (2002), Beheshti (2003) or Kolar (2005), Medelyanand Witten (2005, 2008, El-Haj, et al 2013, Willis and Losee (2013), who draw on no fewer than four thesaurusi (AGROVOC, HEP, NALT and MeSH) to evaluate their algorithm, Pickler and Ferneda (2014), Vlachidis and Tudhope (2016) or Dehghani (2015).…”