Sinai RusinekpersName, Tomer SagipersName, Moran ZagapersName, Efraim LevpersName, Moshe LaveepersName (2023date). “MEHDIE: The Middle East Heritage Data Integration Endeavor.” Digital Humanities 2023 (DH2023), Graztitle·a, GrazplaceName.
Object of study — Historical place names in Hebrew, Arabic and Syriac sources, and the problem of deciding when two of them denote the same place.
Research question — Can historical Middle Eastern datasets be linked by matching place names directly between the domain's own languages, rather than by transliterating them into Latin script or routing them through a general-purpose gazetteerterm·dom?
Contribution — Argues, from a worked example, that a general authority fileterm·dom under-covers a specialist domain's own vocabulary, and that intra-domainterm·mth matching beats routing through a central one.
phenomenon · claim-type · cross-domain-transfer · mechanism · claim-relation · replication-status · limitation — grounded in the full text| phenomenon | cross-lingual toponym entity matching — “The mission to connect data on the Middle eastern history domain is faced with special challenges: the scarcity of vowels in Semitic scripts, the indeterminacy of pronunciation and transliteration of written toponyms, and varying practices of naming and classifying places.” | |
| claim-type | method — “We are building a multi-modal entity resolution tool that utilizes the spatial, temporal, and textual information about a pair of place records to help identify the semantic relation between them.” | |
| method — evidence | — “The multi-modal entity resolution tool we are developing will utilise spatial (geo-coordinates), temporal (dates/periods) and textual information about a pair of place/person records to help identify the semantic relationship between them.” | |
| research question — evidence | — “The multi-modal entity resolution tool we are developing will utilise spatial (geo-coordinates), temporal (dates/periods) and textual information about a pair of place/person records to help identify the semantic relationship between them.” | |
| contribution — evidence | — “The advantages of intra-domain transliteration for matching opens a meta-discussion on approaches for linked open data and the preference of a “bottom-up” intra-domain strategy over a centralised one.” | |
| mechanism | Matching uses three kinds of evidence at once - coordinates, dates and the text of the name - rather than name similarity alone — “We are building a multi-modal entity resolution tool that utilizes the spatial, temporal, and textual information about a pair of place records to help identify the semantic relation between them.” | mechanisms[0] |
| mechanism | Transliterating between two Semitic languages preserves the ambiguity of both instead of forcing a decision, which is why it beats going through Latin script — “This shows the power of transliteration between semitic languages that reduces, rather than adds ambiguity: Neither Arabic nor Hebrew explicate the sound that is expressed in English by the first i and the e in the name.” | mechanisms[1] |
| mechanism | Latin transliteration fails because it demands vowels the source scripts never wrote — “Therefore, transliteration to latin script could not deduce an acceptable transliteration.” | mechanisms[2] |
| mechanism | Every candidate match is returned with a confidence and an account of which method produced it, so a human can judge it — “Also visible in the figure are the confidence measure and the explanation of the matching methods that yielded the candidate.” | mechanisms[3] |
| extends | World Historical Gazetteer (Grossner and Mostern 2021) — “In the demonstration we present tools related to spatial data, which we hope to integrate into the World Historical Gazetteer (Grossner and Mostern 2021) system to enhance its capabilities for inter-dataset matching.” | claim_relations[0] |
| builds-on | Historical Middle East Data Alliance (Hist-ME) — “The system we are developing at MEHDI facilitates collaboration between Hist-ME ’s partners towards this vision.” | claim_relations[1] |
| extends | the World Historical Gazetteer, which the matching tools are intended to enhance — “In the demonstration we present tools related to spatial data, which we hope to integrate into the World Historical Gazetteer (Grossner and Mostern 2021) system to enhance its capabilities for inter-dataset matching.” | claim_relations[2] |
| supports | the Hist-ME vision of connecting monolingual and intra-religious data silos — “The Historical Middle East Data Alliance (Hist-ME) was initiated by Nathan P. Gibson at the Linked Pasts 2021 conference with a joint vision of connecting intra-religious and monolingual silos of disconnected data into a linked contextual wealth of knowledge.” | claim_relations[3] |
| critiques | reconciliation to general-purpose external gazetteers as the default linked-data strategy — “Such general gazetteers may include contemporary Arabic, Hebrew or Syriac forms that denote major, well known cities, but very little historic variants of the lesser known settlements.” | claim_relations[4] |
| sense | transliteration - into Latin script: the usual move, which fails here because it requires vowels the source never wrote — “Therefore, transliteration to latin script could not deduce an acceptable transliteration.” | senses[0] |
| sense | transliteration - between Semitic languages: preserves the same indeterminacy on both sides, so it narrows candidates instead of multiplying them — “The similarity between semitic languages, however, means that direct transliteration between semitic languages would be much more efficient in creating candidates for matching that transliteration into Latin script languages.” | senses[1] |
| sense | the place name - as written in a nineteenth-century edition: בלביש, with an archaic final consonant — “The Hebrew toponym for the city of Bilbeis on the Nile’s delta (spelled “Bilbays” in Adler’s translation of Benjamin of Tudela) was mentioned in the 19th century edition of Benjamin of Tudela’s itinerary in the Hebrew form בלביש.” | senses[2] |
| sense | the place name - as written in contemporary Hebrew: בילביס, with an added vowel and a different final letter - and the authority holds only this one — “Wikidata currently includes a Hebrew alternative variant without the additional vowel, but not a variant with the more archaic letter ‘ ש’ (Wikidata contributors, "Q393495").” | senses[3] |
| sense | linked data strategy - centralised: reconcile every source to one external authority, which is the default assumption — “A common way to identify places, their locations and other information about them is to reconcile the source place names with unique identifiers from an external Gazetteer.” | senses[4] |
| sense | linked data strategy - bottom-up and intra-domain: match the domain's datasets against each other first, which this paper argues for — “The advantages of intra-domain transliteration for matching opens a meta-discussion on approaches for linked open data and the preference of a “bottom-up” intra-domain strategy over a centralised one.” | senses[5] |
| audit | transliteration —operationalised-as→ entity resolution — Audit 2026-09-28: DOUBTFUL - read against its span and kept, but transliteration enabled matching; 'entity resolution' is the task, and operationalised-as overstates it. — “Using the transliteration tool in our system to match against Arabic datasets such as Usaybia , Damast , ‘Al-Ṯurayya gazetteer (Romanov and Seydi, 2019) and from a dataset of toponyms from Yaqut al-Hamawi’s Mu 'jam ul-Buldān, we could easily find the match thanks to the transliteration of the Hebrew form to the Arabic form بلبيس, one of two possible transliterations.” | concept_edges[0] |
| audit | Geonames —is-a→ gazetteer — Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but endpoint by anaphora: 'two such resources' = external Gazetteers (previous sentence). — “Geonames and the Getty Thesaurus of geographic names are two such resources, but they contain few, if any, toponyms in the Semitic scripts relevant to the sources of Middle Eastern History.” | concept_edges[3] |
| audit | Getty Thesaurus of geographic names —is-a→ gazetteer — Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but endpoint by anaphora: 'two such resources' = external Gazetteers (previous sentence). — “Geonames and the Getty Thesaurus of geographic names are two such resources, but they contain few, if any, toponyms in the Semitic scripts relevant to the sources of Middle Eastern History.” | concept_edges[4] |
| audit | gazetteer —operationalised-as→ entity resolution — Audit 2026-09-28: DOUBTFUL - read against its span and kept, but reconciling names against a gazetteer is described; 'entity resolution' is the tagger's term for it. — “A common way to identify places, their locations and other information about them is to reconcile the source place names with unique identifiers from an external Gazetteer.” | concept_edges[6] |
| weight | gazetteer —operationalised-as→ entity resolution — 0.9 — “A common way to identify places, their locations and other information about them is to reconcile the source place names with unique identifiers from an external Gazetteer.” | concept_edges[6] |
| audit | World Historical Gazetteer —is-a→ gazetteer — Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but is-a rests on the word 'Gazetteer' inside the name. — “In the demonstration we present tools related to spatial data, which we hope to integrate into the World Historical Gazetteer (Grossner and Mostern 2021) system to enhance its capabilities for inter-dataset matching.” | concept_edges[8] |
| for which use | limitation — any reliance on general gazetteers for this domain: GEONAMES AND THE GETTY THESAURUS ... CONTAIN FEW, IF ANY, TOPONYMS IN THE SEMITIC SCRIPTS relevant to the sources — “Geonames and the Getty Thesaurus of geographic names are two such resources, but they contain few, if any, toponyms in the Semitic scripts relevant to the sources of Middle Eastern History.” | limitations[0] |
| for which use | limitation — Wikidata reconciliation specifically: EVEN WIKIDATA, WHICH IS ESSENTIALLY MULTILINGUAL, SHOWS LOW RECALL WHEN MATCHING AGAINST THEM — “Even Wikidata, which is essentially multilingual, shows low recall when matching against them.” | limitations[1] |
| for which use | limitation — the coverage that general resources do provide: they include forms that DENOTE MAJOR, WELL KNOWN CITIES, BUT VERY LITTLE HISTORIC VARIANTS OF THE LESSER KNOWN SETTLEMENTS — “Such general gazetteers may include contemporary Arabic, Hebrew or Syriac forms that denote major, well known cities, but very little historic variants of the lesser known settlements.” | limitations[2] |
| for which use | limitation — every matching result in the domain: THE SCARCITY OF VOWELS IN SEMITIC SCRIPTS, THE INDETERMINACY OF PRONUNCIATION AND TRAN[sliteration] make the problem hard before any tool is applied — “The mission to connect data on the Middle eastern history domain is faced with special challenges: the scarcity of vowels in Semitic scripts, the indeterminacy of pronunciation and transliteration of written toponyms, and varying practices of naming and classifying places.” | limitations[3] |
| for which use | limitation — any successful match treated as unique: the Hebrew-to-Arabic transliteration used was ONE OF TWO POSSIBLE TRANSLITERATIONS — “we could easily find the match thanks to the transliteration of the Hebrew form to the Arabic form بلبيس, one of two possible transliterations” | limitations[4] |
| replication | untested | |
| limitation | General gazetteers barely cover the Semitic-script toponyms this domain runs on — “Geonames and the Getty Thesaurus of geographic names are two such resources, but they contain few, if any, toponyms in the Semitic scripts relevant to the sources of Middle Eastern History.” | limitations[0] |
| limitation | Even Wikidata, which is multilingual by design, matches poorly against these sources — “Even Wikidata, which is essentially multilingual, shows low recall when matching against them.” | limitations[1] |
| limitation | Where general resources do cover the domain it is the major cities, not the smaller settlements or the historic variants — “Such general gazetteers may include contemporary Arabic, Hebrew or Syriac forms that denote major, well known cities, but very little historic variants of the lesser known settlements.” | limitations[2] |
| limitation | The domain's own scripts make the problem harder before any tool is applied: missing vowels, uncertain pronunciation, and no settled naming practice — “The mission to connect data on the Middle eastern history domain is faced with special challenges: the scarcity of vowels in Semitic scripts, the indeterminacy of pronunciation and transliteration of written toponyms, and varying practices of naming and classifying places.” | limitations[3] |
| limitation | Even the successful transliteration is one of several possible forms, not a unique answer — “we could easily find the match thanks to the transliteration of the Hebrew form to the Arabic form بلبيس, one of two possible transliterations” | limitations[4] |
finding · quantity · variable · definition · key-term — grounded in the full text| finding | General-purpose gazetteers carry almost none of the Semitic-script toponyms that Middle Eastern historical sources actually use. — “Geonames and the Getty Thesaurus of geographic names are two such resources, but they contain few, if any, toponyms in the Semitic scripts relevant to the sources of Middle Eastern History.” | content_tags.findings[0] |
| finding | Wikidata, although multilingual, also matches these sources poorly. — “Even Wikidata, which is essentially multilingual, shows low recall when matching against them.” | content_tags.findings[1] |
| finding | A concrete gap: Wikidata holds a modern Hebrew variant of the toponym but not the archaic spelling the historical source uses. — “Wikidata currently includes a Hebrew alternative variant without the additional vowel, but not a variant with the more archaic letter” | content_tags.findings[2] |
| finding | transliteration between Semitic languages reduces rather than adds ambiguity — “This shows the power of transliteration between semitic languages that reduces, rather than adds ambiguity” | content_tags.findings[3] |
| finding | The authors draw a general conclusion for linked open data: prefer a bottom-up, intra-domain strategy over a centralised one. — “opens a meta-discussion on approaches for linked open data and the preference of a “bottom-up” intra-domain strategy over a centralised one” | content_tags.findings[4] |
| finding | general gazetteers including Wikidata have low recall against Semitic-script historical toponyms — “Even Wikidata, which is essentially multilingual, shows low recall when matching against them.” | content_tags.findings[5] |
| finding | transliteration between Semitic languages reduces rather than adds ambiguity: neither Arabic nor Hebrew writes the vowel sounds that English spells with the first i and the e — “This shows the power of transliteration between semitic languages that reduces, rather than adds ambiguity: Neither Arabic nor Hebrew explicate the sound that is expressed in English by the first i and the e in the name.” | content_tags.findings[6] |
| finding | Wikidata holds a modern Hebrew variant of the toponym but not the variant with the archaic letter ש. — “Wikidata currently includes a Hebrew alternative variant without the additional vowel, but not a variant with the more archaic letter ‘ ש’ (Wikidata contributors, "Q393495").” | content_tags.findings[7] |
| finding | the results may also argue for collaboration within the domain — “The results of our work with the different datasets of Hist-ME member projects may also constitute an argument in favour of intra-domain collaboration.” | content_tags.findings[8] |
| definition | MEHDIE — “MEHDIE , the Middle East Heritage Data Integration Endeavour is a project at Haifa University and Aalborg University, dedicated to facilitating semantic integration of knowledge sources related to the history of the Middle East, using innovative data integration methods.” | content_tags.definitions[1] |
| definition | Hist-ME — “The Historical Middle East Data Alliance (Hist-ME) was initiated by Nathan P. Gibson at the Linked Pasts 2021 conference with a joint vision of connecting intra-religious and monolingual silos of disconnected data into a linked contextual wealth of knowledge.” | content_tags.definitions[2] |
| key-terms | entity resolution, gazetteer, toponym, transliteration, Wikidata, Semitic scripts, linked open data, toponyms, multilinguality, World Historical Gazetteer, Geonames, confidence measure, Hist-ME, intra-domain |
| phenomenon | cross-lingual toponym entity matching — a second reading reaching the same value; recorded: cross-lingual toponym entity matching — “MEHDIE , the Middle East Heritage Data Integration Endeavour is a project at Haifa University and Aalborg University, dedicated to facilitating semantic integration of knowledge sources related to the history of the Middle East, using innovative data integration methods.” | alternatives.phenomenon |
Full text — tagged
The reference list is not part of the text we hold for this paper. Our copy was extracted from the publisher's page and the bibliography did not survive that extraction, so the article below ends before its references. Nothing has been removed by us.
MEHDIEterm·def: The Middle East Heritage Data Integration Endeavor RusinekpersName Sinai Haifa University, Israel sinai.rusinekpersName@mail.huji.ac.il Digital Humanities 2023. Collaboration as Opportunity Graz SagipersName Tomer Haifa University, Israel tsagi@cs.aau.dk Digital Humanities 2023. Collaboration as Opportunity Graz ZagapersName Moran Haifa University, Israel moran82@gmail.com Digital Humanities 2023. Collaboration as Opportunity Graz LevpersName Efraim Haifa University, Israel elev@univ.haifa.ac.il Digital Humanities 2023. Collaboration as Opportunity Graz Moshe LaveepersName Haifa University, Israel mlavee@univ.haifa.ac.il Digital Humanities 2023. Collaboration as Opportunity Graz Zentrum für Informationsmodellierung - Austrian Centre for Digital Humanities, Karl-Franzens-Universität Graz 2023 Graz Creative Commons BY 4.0 Digital Humanities 2023: Book of Abstracts Walter Scholger University of Graz Graz, Austria walter.scholger@uni-graz.at Georg Vogeler University of Graz Graz, Austria georg.vogeler@uni-graz.at Toma Tasovac Belgrade Center for Digital Humanities Belgrade, Serbia ttasovac@humanistika.org Anne Baillot Le Mans Université Le Mans, France anne.baillot@univ-lemans.fr Data Management Elisabeth Raunig Data Management Martina Scholger Data Management Elisabeth Steiner Data Curation Johanna Ofenauer Data Curation Christina Burgstaller 10.5281/zenodo.7961822 Converted from a Word document DHConvalidator We are building a multi-modal entity resolutionterm·mth tool that utilizes the spatial, temporal, and textual information about a pair of place records to help identify the semantic relation between them. We plan to share our progress towards the integration of knowledge sources related to the history of the Middle East.
English Paper Poster entity matching multilingualityterm·key gazetteersterm·dom transliterationterm·mth toponymsterm·dom information retrieval and querying algorithms and methods linked (open) data spatial & spatio-temporal analysis modeling and visualization Geography and geo-humanities History MEHDIEterm·def , the Middle East Heritage Data Integration Endeavour is a project at Haifa University and Aalborg University, dedicated to facilitating semantic integration of knowledge sources related to the history of the Middle East, using innovative data integration methods.
The multi-modal entity resolutionterm·mth tool we are developing will utilise spatial (geo-coordinates), temporal (dates/periods) and textual information about a pair of place/person records to help identify the semantic relationship between them. In the demonstration we present tools related to spatial data, which we hope to integrate into the World Historical Gazetteerterm·mth (Grossner and Mostern 2021) system to enhance its capabilities for inter-dataset matching. The poster will address our workflows for data extraction and assembly, as well as the results of matching experiments between various datasets . We describe how we leverage the linguistic affinities and continuities between the domain languages and various textual matching techniques.
In figure 1 we see the interface of the MEHDIEterm·def clone of the World Historical Gazetteerterm·mth, with the added option to match two datasets against each other, in this case a dataset of the Hebrew toponymsterm·dom from Benjamin of Tudelaterm’s travelog collected in the framework of the TraveLab project (RusinekpersName and Shalit 2022), and Damastterm Multilingual Dataset from the Dhimmis and & Muslims project (Franke and Kock 2023). Also visible in the figure are the confidence measureterm·mth and the explanation of the matching methods that yielded the candidate.
The mission to connect data on the Middle eastern history domain is faced with special challenges: the scarcity of vowels in Semitic scriptsterm·dom, the indeterminacy of pronunciation and transliterationterm·mth of written toponymsterm·dom, and varying practices of naming and classifying places.
A common way to identify places, their locations and other information about them is to reconcile the source place names with unique identifiers from an external Gazetteerterm·dom. Geonamesterm·mth and the Getty Thesaurus of geographic namesterm·mth are two such resources, but they contain few, if any, toponymsterm·dom in the Semitic scriptsterm·dom relevant to the sources of Middle Eastern History. Even Wikidataterm·mth, which is essentially multilingual, shows low recall when matching against them. Such general gazetteersterm·dom may include contemporary Arabic, Hebrew or Syriac forms that denote major, well known cities, but very little historic variants of the lesser known settlements. With this obstacle in mind, one may turn to transliterationterm·mth. The similarity between semitic languages, however, means that direct transliterationterm·mth between semitic languages would be much more efficient in creating candidates for matching that transliterationterm·mth into Latin script languages.
The example in figure 2 is a telling illustration for this: The Hebrew toponymterm·dom for the city of Bilbeis on the Nile’s delta (spelled “Bilbays” in Adler’s translation of Benjamin of Tudelaterm) was mentioned in the 19th century edition of Benjamin of Tudelaterm’s itinerary in the Hebrew form בלביש. In contemporary Hebrew it is spelled בילביס, with an additional vowel and a different letter to represent the final consonant. Wikidataterm·mth currently includes a Hebrew alternative variant without the additional vowel, but not a variant with the more archaic letter ‘ ש’ (Wikidataterm·mth contributors, "Q393495").
Using the transliterationterm·mth tool in our system to match against Arabic datasets such as Usaybia , Damastterm , ‘Al-Ṯurayya gazetteerterm·dom (Romanov and Seydi, 2019) and from a dataset of toponymsterm·dom from Yaqut al-Hamawi’s Mu 'jam ul-Buldān, we could easily find the match thanks to the transliterationterm·mth of the Hebrew form to the Arabic form بلبيس, one of two possible transliterationsterm·mth. This shows the power of transliterationterm·mth between semitic languages that reduces, rather than adds ambiguity: Neither Arabic nor Hebrew explicate the sound that is expressed in English by the first i and the e in the name. Therefore, transliterationterm·mth to latin script could not deduce an acceptable transliterationterm·mth.
Several projects have been dedicated in recent years to the aggregation of geographic and prosopographicterm·dom data on Middle Eastern History. The Historical Middle East Data Alliance (Hist-MEterm·dom) was initiated by Nathan P. Gibson at the Linked Pasts 2021 conference with a joint vision of connecting intra-religious and monolingual silos of disconnected data into a linked contextual wealth of knowledge. The system we are developing at MEHDI facilitates collaboration between Hist-MEterm·dom ’s partners towards this vision.
The advantages of intra-domainterm·mth transliterationterm·mth for matching opens a meta-discussion on approaches for linked open dataterm·dom and the preference of a “bottom-up” intra-domainterm·mth strategy over a centralised one. The results of our work with the different datasets of Hist-MEterm·dom member projects may also constitute an argument in favour of intra-domainterm·mth collaboration.