D15.3 Report on Semantic Annotation and Linking

! ! ! ! D15.3&Report&on&Semantic& Annotation&and&Linking&& Version!1.0! January!2017! ! ! Grant!Agreement!number:!! 313193! Project!acronym:!! ARIADNE! Project!title:!! Advanced!Research!Infrastructure!for!Archaeological!Dataset!Networking! in!Europe! Funding!Scheme:!! FP7-INFRASTRUCTURES-2012-1! Project!co-ordinator:! Franco!Niccolucci,!PIN!Scrl!-!Polo!Universitario!"Città!di!Prato"! Tel:!! +39!0574!602578! E-mail:!! [email protected]! Project!website!address:!! http://www.ariadne-infrastructure.eu!! ! ! ! ! ! !! ! ! ! ! ! ! ! ! ! ARIADNE!is!a!project!funded!by!the!European!Commission!under!the!Community’s!Seventh! Framework! Programme,! contract! no.! FP7-INFRASTRUCTURES-2012-1-313193.! The! views! and!opinions!expressed!in!this!report!are!the!sole!responsibility!of!the!authors!and!do!not! necessarily!reflect!the!views!of!the!European!Commission.! ! ! ARIADNE!–!D15.3:!Report!on!Semantic!Annotation!and!Linking!Prepared!by!USW! ARIADNE! 2! January!2017! ! About&this&document& This! document! is! a! contractual! deliverable!of! the!ARIADNE! project.! The! research! leading! to! these! results!has!received!funding!from!the!European!Community's!Seventh!Framework!Programme!(FP7INFRASTRUCTURES-2012-1)! under! grant! agreement! n°! 313193.!But! the! content! of! this! document! cannot!be!considered!to!reflect!the!views!of!the!European!Commission.! Partner!in!charge!of!the! deliverable:! University!of!South!Wales!(USW)! Authors:! Douglas!Tudhope!(USW)! Ceri!Binding!(USW)! Contributors:! Dimitris!Gavrilis!(ATHENA!RC)! Paul!Boon,!Hella!Hollander!(KNAW-DANS)! Jeremy!Azzopardi!(SND)! Andreas!Vlachidis!(USW)! Guntram!Geser!(SRFG)! Quality!review:! Franco!Niccolucci!and!Paola!Ronzino!(PIN)!! ! & & & & & ! ARIADNE!–!D15.3:!Report!on!Semantic!Annotation!and!Linking!Prepared!by!USW! ARIADNE! 3! January!2017! ! Table&of&content& ! 1&Executive&Summary&....................................................................................................................&4& 2&Semantic&annotation&and&linking&within&ARIADNE&......................................................................&5& 2.1&Semantic!linking!in!the!spatial!dimension!..................................................................................!5& 2.2&Semantic!linking!in!the!temporal!dimension!..............................................................................!5& 2.3&Semantic!linking!in!the!subject!dimension!.................................................................................!6& 2.4&Semantic!linking!tools!in!the!subject!dimension!........................................................................!7& 2.4.1&Vocabulary!mapping!tools!relevant!to!WP15!................................................................................!7& 2.4.2&Vocabulary!mapping!tools!in!ARIADNE!..........................................................................................!9& 2.4.3&Vocabulary!mappings!conducted!for!ARIADNE!............................................................................!11& 2.4.4&Vocabulary!mappings!within!the!ARIADNE!portal!.......................................................................!12& 2.5&Wood/Dendrochronology!case!study!on!item!level!data!integration!......................................!13& 3&Summary&and&lessons&learned&..................................................................................................&17& 4&References&...............................................................................................................................&19& ! ! ! ! ARIADNE!–!D15.3:!Report!on!Semantic!Annotation!and!Linking!Prepared!by!USW! ARIADNE! 4! January!2017! ! ! 1 Executive*Summary* Brief&summary& The!review!and!development!work!described!in!this!report!focuses!on!the!aspects!of!semantic!linking! and! annotation! particularly! relevant! to! ARIADNE.! Semantic! linking! within! ARIADNE! is! considered! within!the!spatial,!temporal!and!subject!dimensions.!The!subject!dimension!is!considered!in!depth,! starting!with!a!review!of!linking!tools!considered!relevant!to!ARIADNE!followed!by!a!discussion!of!the! ARIADNE!approach!and!the!vocabulary!mapping!tools!used!within!ARIADNE.!The!Getty!AAT!proved! an!appropriate!vocabulary!mapping!hub!that!afforded!a!multilingual!search!capability!in!the!ARIADNE! Portal!via!the!semantic!enrichment!of!partner!subject!metadata!with!derived!AAT!concepts.!! A! case! study! conducted! an! exploratory! investigation! of! the! semantic! integration! of! extracts! from! archaeological! datasets! with! information! extracted! via! NLP! across! different! languages.! The! investigation!followed!a!broad!theme!relating!to!wooden!material!including!shipwrecks,!with!a!focus! on!types!of!wooden!material,!samples!taken,!wooden!objects!with!dating!from!dendrochronological! analysis,!etc.!The!Demonstrator!is!available!for!general!use.!The!user!is!shielded!from!the!complexity! of! the! underlying! semantic! framework! (based! on! the! CIDOC! CRM! and! Getty! AAT)! by! the! Web! application!user!interface.!The!Demonstrator!highlights!the!potential!for!archaeological!research!that! can!interrogate!grey!literature!reports!in!conjunction!with!datasets.!Queries!concern!wooden!objects! (e.g.!samples!of!beech!wood!keels),!optionally!from!a!given!date!range,!with!automatic!expansion! over!hierarchies!of!wood!types.! Lessons&learned& o The!spatial,!temporal!and!subject!dimensions!are!key!to!archaeology!and!the!main!vehicle!for! semantic! linking.! Cleansing! and! normalisation! via! semantic! enrichment! is! necessary! in! each! dimension.! o The! Getty! AAT! proved! an! appropriate! vocabulary! mapping! hub! that! afforded! a! multilingual! search!capability!in!the!ARIADNE!Portal.! o The!Wood/Dendrochronology!case!study!demonstrated!the!feasibility!of!connecting!information! (at! a! detailed! level)! extracted! from! datasets! and! grey! literature! reports! in! different! languages! and! semantic! cross-searching! of! the! integrated! information.! The! case! study! suggests! that! the! semantic! linking! of! textual! reports! and! datasets! opens! up! possibilities! for! integrative! archaeological!research!across!diverse!resources.! o The! Wood/Dendrochronology! demonstrator! shows! that! a! Web! application! can! hide! the! complexity! of! the! underlying! semantic! framework! from! the! user! and! allow! querying! and! browsing! the! information! without! expertise! in! SPARQL;! it! illustrates! that! more! intuitive! user! interfaces!are!possible!for!searching!RDF!datasets!than!the!usual!SPARQL!endpoint!or!browsing! hyperlinks.! ! ! ! ! ARIADNE!–!D15.3:!Report!on!Semantic!Annotation!and!Linking!Prepared!by!USW! ARIADNE! 5! January!2017! ! ! 2 Semantic*annotation*and*linking*within*ARIADNE** Semantic! annotation!is! covered! in! part! by! the! ARIADNE! Natural! Language! Processing! (NLP)! work! reported!under!WP16.!For!more!information!on!automatic!text!annotation!(and!text-mining)!within! archaeology,!including!machine!learning!outcomes!from!the!ADS!ArchaeoTools!Project!and!the!rulebased! OPTIMA! toolkit! from! the! USW! STAR! Project,! see! Richards!et! al.!(2015)! and! the! deliverable! ARIADNE!D16.4!-!Final!Report!on!Natural!Language!Processing,!which!also!reports!on!NLP!outcomes! from! ARIADNE.! One! strand! of! these! outcomes! contributed! to! the! Wood/Dendrochronology! data! integration!case!study!and!Demonstrator,!which!combines!semantic!links!between!datasets!and!(via! NLP)!archaeological!reports.!This!is!discussed!below.! In! archaeology,! semantic! linking!generally! involves! connections! (usually! semi-automatic! with! intellectual! review)! between! archaeological! resources! via! an! intermediary! knowledge! organization! system!covering!relevant!aspects!of!the!space,!time!and!subject!dimensions.!Semantic!linking!in!the! subject!dimension!is!discussed!below!as!regards!mapping!between!subject!thesauri!and!controlled! vocabularies,!while!linking!via!the!CIDOC!CRM!core!ontology,!is!discussed!in!ARIADNE!D14.2!-!Pilot! Deployment!Experiments.! 2.1 Semantic*linking*in*the*spatial*dimension* For!ARIADNE,!a!key!component!of!the!strategy!for!the!spatial!domain!has!been!the!adoption!of!a! standard!format!for!spatial!coordinates,!WGS84.!Different!partners!employ!different!local!coordinate! systems!which!are!normalised!to!WGS84.!Normalised!spatial!coordinates!constitute!the!main!spatial! access!method!in!the!ARIADNE!Portal.!Relevant!gazetteers!of!place!names,!including!GeoNames!and! TGN,!are! discussed!in! ARIADNE!D3.1! -! Initial! report! on! standards! and! on! the! project! registry.! The! work!of!the!Pelagios!project!has!been!a!significant! contributor! to! the! Digital! Humanities! arena! of! spatial!linked!data,!including!various!workshops!in!the!Linked!Pasts!series.!Pelagios!makes!use!of!the! Pleiades! gazetteer1!(and! its! URIs)! to! connect! online! resources! that! refer! to! places! in! the! ancient! world!via!Linked! Open!Data.!Pelagios!does!not!attempt! to!define! a!complex!data!model,! rather! it! seeks!to! offer!a!uniform!way! to!build!links!between!different!gazetteers!via! the!Open!Annotation! Ontology.!Pelagios!metadata!aims!to!support!interoperability!while!imposing!minimal!overheads!on! data!providers.!Pelagios!is!developing!various!tools!(beta!at!time!of!writing),!including!Recogito2!,!an! annotation!platform!for!annotating!images,!creating!maps,!linking!research!data!to!the!wider!web!of! data,!the!Pelagios!Map!Tiles!mapping!application,!the!Peripleo!search!service!and!API3!.!Various!other! efforts!are!ongoing!in!the!second!phase!of!the!Pelagios!project,!which!aims!to!encourage!community! participation! in! the! enterprise:! “Pelagios! Commons! provides! online! resources! and! a!community! forum!for!using!open!data!methods!to!link!and!explore!historical!places”4.! 2.2 Semantic*linking*in*the*temporal*dimension* In! the! temporal! domain,! ARIADNE! made! the! decision! to! adopt! the! recently! emerged! PeriodO! gazetteer!as!a!central!hub!for!expressing!standard!period!definitions,!in!order!to!link!and!visualize! !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! 1!Pleiades,!https://pleiades.stoa.org!! 2!Recogito,!http://recogito.pelagios.org!! 3!Peripleo,!https://github.com/pelagios/peripleo#peripleo-api!! 4!Pelagios,!http://commons.pelagios.org!! ! ARIADNE!–!D15.3:!Report!on!Semantic!Annotation!and!Linking!Prepared!by!USW! ARIADNE! 6! January!2017! ! time! period! data.! “PeriodO! is! a! gazetteer! of! scholarly! definitions! of! historical,! art-historical,! and! archaeological!periods.!It!eases!the!task!of!linking!among!datasets!that!define!periods!differently.!It! also! helps! scholars! and! students! see! where! period! definitions! overlap! or! diverge”! (PeriodO)5.! A! ‘period’! is! of! course! a! complex! archaeological! concept,! which! can! encompass! timespans,! spatial! extents!and!sometimes! cultural!forms! (Niccolucci!&! Hermon! 2015).!PeriodO!defines!a! data!model! that! includes! a! name! for! the! period,! some! temporal! bounds,! an! association! with! a! geographical! region! and! which! has! some! literary! warrant! (Shaw! 2015;! Shaw! et! al.! 2015).! The! PeriodO! Client6! allows!users!to!browse!the!PeriodO!dataset!of!periods,!compare!different!period!definitions,!extract! the!URI!for!a!period,!extract!semantically!structured!data!(JSON-LD),!submit!new!periods!or!update! existing!ones!the!user!has!previously!entered.!!ARIADNE!partners!expressed!temporal!metadata!for! archaeological!periods!using!local!vocabularies,!with!start!and!end!dates!for!each!term.!The!unified! list! of! ARIADNE! period! vocabularies! was! made! available! to! PeriodO! in! a! collaboration! with! that! project.!This!resulted!in!the!ARIADNE!collection!of!period!definitions!in!PeriodO7,!where!URIs!identify! each!period!and!distinguish!the!meaning!of!a!period!name!in!different!places.! 2.3 Semantic*linking*in*the*subject*dimension* Much!of!the!effort!of!WP15!has!concerned!semantic!linking!in!the!subject!domain.!Mapping!between! subject!thesauri!and!other!controlled!vocabularies!is!an!important!contributor!to!interoperability!and! cross!search!in!disciplines!with!diverse!datasets,!such!as!archaeology,!and!is!particularly!important! for!multilingual!capability!(see!the!review!in!Zeng!&!Chan!2004).!ARIADNE!D15.1!gives!an!overview!of! vocabulary! mapping! drawing! on! the! ISO! thesaurus! standard! (ISO! 25964-2:2013),! discussing! the! rationale!of!vocabulary!mapping!within!ARIADNE!and!the!choice!of!the!Getty!Art!and!Architecture! Thesaurus!(AAT)8!as!a! mapping!hub.!The! AAT!is!available!as!Linked!Open!Data!in!SKOS,!published! under! the! Open! Data! Commons! Attribution! License! (ODC-By)! 1.09.! The! AAT! contains! over! 40,000! concepts! and! over! 350,000! terms,! organised! in! seven! facets! (and! 33! hierarchies! as! subdivisions):! Associated!concepts,!Physical!attributes,!Styles!and!periods,!Agents,!Activities,!Materials,!Objects!and! optional! facets! for! time! and! place! (Harpring! 2016).! The! AAT’s! scope! is! broader! than! archaeology,! encompassing! visual! art,!architecture,! other! material! heritage,! archaeology,! conservation,! archival! materials,!etc.,!but!contains!many!useful!high!level!archaeological!concepts,!particularly!in!the!Built! Environment,!Materials!and!Objects!hierarchies.! Different!partner!subject!vocabularies!are!mapped!to!the!AAT,!which!then!forms!the!basis!for!search! across! indexing! vocabularies! in! different! languages.! The! major! exercise! mapping! between! partner! native!vocabularies!and!the!AAT!as!a!central!hub!is!described!in!D15.1,!including!reflections!on!the! mapping!process.!The!creation!of!links!directly!between!the!items!from!different!vocabularies!can! become!unmanageable!as!the!number!of!vocabularies!increases.!A!scalable!solution!is!to!employ!a! hub! architecture,! an! intermediate! structure! on! to!which! concepts! from! ARIADNE! data! provider! source! vocabularies! can! be! mapped.! The! benefits! of! vocabulary! mapping! are! clear! for! collections! with!multilingual!metadata!and!content.!By!using!the!AAT!as!a!central!hub,!a!semantic!search!on!an! AAT! concept! can! retrieve! results! originally! indexed! by! terms! from! various! languages! (Binding! and! !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! 5!PeriodO,!http://perio.do,!https://github.com/periodo!! 6!PeriodO!client,!http://n2t.net/ark:/99152/p0!! 7!ARIADNE!collection!of!period!definitions!in!PeriodO,!http://n2t.net/ark:/99152/p0qhb66!! 8!Getty!Art!and!Architecture!Thesaurus,!http://www.getty.edu/research/tools/vocabularies/aat/!! 9!Getty!Vocabularies!as!Linked!Open!Data,!http://www.getty.edu/research/tools/vocabularies/lod/index.html!! ! ARIADNE!–!D15.3:!Report!on!Semantic!Annotation!and!Linking!Prepared!by!USW! ARIADNE! 7! January!2017! ! Tudhope!2016).!This!can!potentially!improve!recall!(indexing!in!several!languages)!and!precision!(in! literal!string!search,!false!results!may!arise!from!homographs).! 2.4 Semantic*linking*tools*in*the*subject*dimension* ARIADNE!D15.3!is!concerned!with!the!tools!employed!for!semantic!linking.!While!some!very!specific! links! between! specific! datasets,! or! specific! cross! references! between! reports,! will! exist,! most! semantic!linking!in!the!subject!dimension!is!achieved!via!the!core!ontology!!(CIDOC!CRM)!and!the! Getty! AAT,! which! have! been! adopted! as! ARIADNE! linking! standards.! Before! describing! the! tools! employed! for! mapping! vocabularies! in! ARIADNE,! we! briefly! review! other! relevant! vocabulary! mapping!tools.! 2.4.1 Vocabulary*mapping*tools*relevant*to*WP15* The!VocBench!publishing!platform!of!the!UN’s!FAO!has!seen!a!major!SKOS!Linked!Data!effort!in!the! agricultural! domain,! mapping!the! multilingual! AGROVOC!thesaurus!to! (at!the! last!count)!13! other! thesauri! (Caracciolo! et! al.! 2012! and! 2013),! including! LCSH! (Library! of! Congress! Subject! Headings),! GEMET!(General!Multilingual!Environmental!Thesaurus)!and!STW!(Standard!Thesaurus!for!Economics! /!Standard!Thesaurus!für!Wirtschaft).!This!has!been!a!long!term!project;!early!work!is!discussed!by! Liang!and!Sini!(2006).! In!ARIADNE,!it!is!possible!to!associate!AAT!concepts!directly!with!partner!subject!metadata!by!taking! account! of! mappings! from! partner! vocabularies! to! the! AAT! created! for! ARIADNE.! In! addition! to! semantic!linking!by!means!of!mapping!between!vocabularies,!it!is!sometimes!necessary!to!associate! concepts!from!controlled!vocabularies!(via!URI!Uniform!Resource!Identifiers)!with!subject!metadata! presented!only!as!free!text.!For!example,!in!the!case!of!a!project!like!Europeana,!which!sometimes! has! to! ingest! subject! metadata! without! knowledge! of! the! original! native! vocabulary! (if! any),! it! is! sometimes! desirable! to! associate! a! controlled! vocabulary! concept! (e.g.! from! the! AAT)! with! potentially! ambiguous,! free! text! metadata,! without! being! able! to! rely! on! a! previous! vocabulary! mapping.! All! that! may! be! available! on! the! source! side! is! the! free! text! subject! label! without! any! further!context!to!take!into!account!from!a!source!vocabulary.!! In!both!these!situations,!the!process!of!associating!a!controlled!vocabulary!concept!is!called!semantic! enrichment.! Enrichment! can! be! considered! a! special! case! of! semantic! annotation.! For! recent! developments! in! Europeana! of! semi-automatic! 'enrichment'! of! free! text! metadata! elements! with! AAT! URIs,! see! Charles! et! al.! (2014).! Stiller! et! al.! (2014)! report! on! a! Europeana! case! study! of! enrichment! with! discussion! of! best! practice.! A! Europeana! Data! Model! case! study! describes! an! example! of! the! enrichment! of! Europeana! data! with! AAT! (Charles! and! Devarenne! 2014).! This! can! bring! benefits! for! multilingual! capability,! for! example! by! automatically! changing! the! subject! metadata!label!displayed!if!the!language!of!the!user!interface!is!changed!by!the!user.! A! specific! MORe! enrichment! service! for! deriving! AAT! concepts! from! partner! vocabularies! was! developed! as! part! of! ARIADNE! utilising! the! AAT! vocabulary! mappings! produced! in! WP15! (see! 'Vocabulary!mappings!conducted!for!ARIADNE'!below!and!ARIADNE!D15.1!-!Report!on!Thesauri!and! Taxonomies).! Various! enrichment! services! have! been! developed! within! the! MORe! aggregation! framework!for!the!LoCloud!project!(Meghini!et!al.,!forthcoming).!These!include:! o Geocoding!based!on!GeoNames;! o Semantic!enrichment,!where!a!vocabulary!matching!service!suggests!SKOS!concepts!based! on!title,!descriptions!and!subject-related!information!in!a!metadata!record;! ! ARIADNE!–!D15.3:!Report!on!Semantic!Annotation!and!Linking!Prepared!by!USW! ARIADNE! 8! January!2017! ! o Wikipedia!and!DBPedia!automatic!enrichment:!a!variation!of!the!semantic!enrichment!that! suggests!Wikipedia!and!DBPedia!entries,!based!on!the!metadata!record;! o Language! identification:! Identifies! languages! based! on! a! title! or! description! using! Apache! Tika;! o Thesauri!mappings:! Allows!loading!and!managing!SKOS!concepts!mappings!from!SKOSified! subject!terms!to!a!target!SKOS!thesaurus.! The! Instance! Matching! application! (SAIM10)! is! a! browser! based! interface! intended! to! support! instance!matching!on!RDF!data,!generally!though!this!is!somewhat!outside!the!focus!of!the!WP15! work.!Consideration!was!also!given!to!the!FP7!supported!Linked!Data!Integration!Framework!(SILK11).! SILK! is! a! sophisticated,! general! semantic! web! framework! for! creating! links! and! not! designed! specifically!for!mapping!thesauri.!A!SILK!‘link!specification’!allows!the!comparison!of!preferred!labels! from! two! thesauri! (using! the! Levenshtein! distance! algorithm).! SILK! is! a! complex! environment! and! there!is!an!inevitable!learning!curve!in!order!to!create!linkage!rules,!transformations,!aggregations! and! in! the! interpretation! of! match! scores.! While! the! SILK!application! is! interactive! and! allows! for! some! comparison,! it! can! be! argued! that! the! main! focus! of! such! tools! tends! to! be! automatic! link! generation! functionality! and! bulk! automation.! The! user! is! not! given! convenient! contextual! information!(specific!to!the!thesauri)!to!facilitate!informed!judgments!on!the!correctness!of!potential! mappings.! Two!archaeological!domain!presentations!at!the!14th!European!Networked!Knowledge!Organization! Systems! (NKOS)! Workshop,! at! TPDL! 2015! in! Poznań! discussed! work! on! SKOS! vocabulary! mapping! using!AMALGAME!(Amsterdam!Alignment!Generation!Metatool12),!developed!at!Free!University!of! Amsterdam! within! the! ClioPatria! framework.! Stahn! (2015)! made! a! pilot! study! with! three! DAI! vocabularies,!expressing!them!as!SKOS!and!then!mapping!via!AMALGAME.!She!makes!the!point!that! the! matching! is! on! string! level! only.! Kempf! (2015)! conducted! experiments! at! ZBW! (Leibniz! Information!Centre!for!Economics)!involving!the!German!STW!Thesaurus!for!Economics!and!an!exact! language!dependent!string!match!on!terms.!A!second!phase!explored!different!types!of!enrichment! of!the!thesaurus!data!before!the!mapping!process,!such!as!descriptors,!synonyms,!results!from!other! mappings.!!The!conclusions!were!that!string!match!could!not!take!account!of!structural!differences! between!the!source!and!target!vocabulary!contexts!but!that!the!experiment!enriching!the!vocabulary! terminology!before!attempting!mapping!offered!useful!potential!candidates!for!further!intellectual! mapping.!AMALGAME!gives!a!choice!of!similarity!metrics!and!properties!to!match!on.!However!the! process!is!then!based!on!automatic!string!match!(although!the!user!does!decide!whether!to!accept!a! mapping)! and! does! not! take! account! of! the! hierarchical! context.! The! work! with! AMALGAME! is! continuing!under!the!new!project!Cultuurlink13,!the!Dutch!Cultural!Heritage!Hub,!where!an!alignment! service! is! offered! for! SKOS! thesauri! and! various! thesauri! are! available.! A! complex,! interactive! alignment!strategy!graphical!editor!is!available.!This!employs!the!AMALGAME!mapping!system!and!a! filter!is!available!that!takes!some!account!of!hierarchical!context.! !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! 10!SAIM,!http://saim.aksw.org!! 11!SILK,!http://wifo5-03.informatik.uni-mannheim.de/bizer/silk!! 12!AMALGAME,!http://semanticweb.cs.vu.nl/amalgame/!! 13!Cultuurlink,!http://cultuurlink.beeldengeluid.nl/app/#/start!! ! ARIADNE!–!D15.3:!Report!on!Semantic!Annotation!and!Linking!Prepared!by!USW! ARIADNE! 9! January!2017! ! 2.4.2 Vocabulary*mapping*tools*in*ARIADNE* Vocabulary!mapping!is!not!a!trivial!exercise.!High!quality!mapping!requires!domain!experts,!who!may! not!have!expertise!in!computing!semantic!technologies.!The!vocabularies!themselves!can!vary!from!a! small!number!of!keywords!from!a!picklist!for!a!particular!dataset!to!standard!national!vocabularies! with!a!large!number!of!concepts.!In!general!at!the!present!time,!fully!automatic!vocabulary!mapping! does! not! currently! deliver! mappings! of! sufficient! operational! quality;! the!ARIADNE! approach! is! to! focus! on! quality! mappings,! in! order! to! support! cross! search! at! a! medium! level! of! generality.! Archaeology!domain!vocabulary!providers!tend!to!have!limited!resources!to!spend!on!the!technical! aspects!of!vocabulary!mapping!tools.!It!is!important!to!support!expert!intellectual!review!and!provide! enough!contextual!data!to!allow!vocabulary!providers!to!make!an!informed!decision!on!the!proposed! mappings.!For!example,!it!might!be!useful!for!the!user!to!compare!thesaurus!structures!side!by!side.!! In! general! for! ARIADNE! purposes,! tools! should! be! light! weight,! user! centered!and! focused! on! thesaurus!to!thesaurus!mapping,!in!order!to!facilitate!user!(vocabulary!provider)!involvement!in!the! mapping! process.! In! some! cases,! ARIADNE! partners! drew! on! their! own! resources! to! create! the! vocabulary!mappings!to! AAT,!for!example!by! directly!browsing!and!searching!the!local! vocabulary! and! the! AAT! or! using! local! utilities! (see! ARIADNE! D15.1).! In! addition,! two! light! weight! tools! were! developed!by!USW!to!support!the!domain!experts!doing!the!mapping!between!vocabulary!concepts,! oriented!to!different!contexts!for!the!vocabularies.!! An! interactive! vocabulary! mapping! tool! was! developed! for! ARIADNE! that! enables! archaeology! subject! experts! create! SKOS! mapping! relationships! between! local! vocabularies! available! online! as! SKOS! and! the! AAT! (Binding! &! Tudhope! 2016).!The! lightweight! Web! application! presents! concepts! from! chosen! source! and! target! vocabularies! side! by! side,! thus! presenting! context! to! allow! an! informed! choice! when! deciding! on! potential! mappings.! The! tool! is! designed! for! vocabularies! expressed!in!RDF/SKOS;!it!queries!external!SPARQL!endpoints!rather!than!storing!local!copies!of!the! vocabularies.!SKOS!mapping!relationships!(Miles!&!Bechofer!2009)!are!employed!for!expressing!the! mappings,!(e.g.!skos:broadMatch!or!skos:closeMatch).!The!resulting!set!of!mappings!can!be!saved! locally,!reloaded!and!exported!to!a!number!of!different!output!formats!(JSON!for!use!in!ARIADNE).! Figure! 1! shows! an! example! where! a! source! concept,! castle,! has! just! been! mapped! to! the! AAT! concept,! castles! (fortification).! The! right! hand! pane! shows! various! AAT! concepts! that! potentially! match!on!the!preferred!term.!The!user!has!selected!the!AAT!concept,!castles!(fortification)!and!both! the! broader! concept! (fortifications)! and! the! narrower! concepts! (châtelets,! moated! castles,! motteand-bailey!castles,!qasrs)!are!displayed,!showing!the!semantic!context!in!a!concise!manner.!Each!of! these!additional!concepts!can!themselves!be!browsed!in!the!tool!to!explore!the!semantic!context.! The!mapping!has!been!considered!a!close!match!by!the!user!and!the!resulting!mapping!is!displayed! at!the!bottom!of!the!screen,!together!with!two!other!recent!mappings.!The!tool!is!available!as!open! source!with!the!code!freely!available!on!GitHub14.! !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! 14!Vocabulary!Matching!Tool!source!code!for!local!download!and!installation,! https://github.com/cbinding/VocabularyMatchingTool!! ! ARIADNE!–!D15.3:!Report!on!Semantic!Annotation!and!Linking!Prepared!by!USW! ARIADNE!16!January!2017! ! underlying! AAT! structure! to! automatically! expand! the! original! query! across! relevant! semantic! relationships,!so!improving!recall!without!sacrificing!precision.!! Figure!6!shows!a!query!on!objects!declared!as!being!of!type!“roofs”,!with!a!production!date!stated!as! being!somewhere!within!the!date!range!1500!to!1600!AD.!The!results!originate!from!data!derived!via! NLP!on!a!textual!report,!indicating!some!instances!where!the!process!has!associated!an!object!with!a! date!(or!a!date!range).!Examination!of!the!textual!notes!associated!with!each!object!suggest!that!the! NLP!results!are!correct.! ! Figure&6:&Search&on&specific&object&type&and&date&range& The! Demonstrator! is! able! to! cross! search! and! browse! information! extracted! from! datasets! and! reports! in! different! languages! via! the! common! framework! based! on! the! CIDOC! CRM! and! AAT;! a! degree! of! semantic! integration! between! data! extracted! from! text! documents! and! databases! has! been!achieved.!In!future!work,!the!intention!is!to!explore!possibilities!of!the!semantic!techniques!for! larger! scale! efforts! on! multilingual! integration! of! datasets! with! reports.! Another! aim! is! to! explore! possibilities! for! more! intuitive! user! interfaces! for! searching! RDF! datasets! than! the! usual! SPARQL! endpoint.!The!Demonstrator!is!available!for!use!via!the!ARIADNE!Portal!services27.!It!is!also!available! as!open!source!with!the!code!freely!available!on!GitHub28.!! !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! 27!Wood/Dendrochronology!Demonstrator,!http://portal.ariadne-infrastructure.eu/services!! 28!Wood/Dendrochronology!Demonstrator!code,!https://github.com/cbinding/ARIADNE-data-integration!! ! ARIADNE!–!D15.3:!Report!on!Semantic!Annotation!and!Linking!Prepared!by!USW! ARIADNE!17!January!2017! ! 3 Summary*and*lessons*learned* Brief*summary* The! review! and! development! work! described! in! this! chapter! focuses! on! the! aspects! of! semantic! linking! and! annotation! particularly! relevant! to! ARIADNE.! The! nature! of! semantic! linking! and! annotation!within!the!ARADNE!context!is!discussed!and!reference!is!made!to!other!relevant!ARIADNE! deliverables.!Semantic!linking!within!ARIADNE!is!considered!within!the!spatial,!temporal!and!subject! dimensions.! The! subject! dimension! is!considered! in! depth,! starting! with! a! review! of! linking! tools! considered! relevant! to! ARIADNE! followed! by! a! discussion! of! the! ARIADNE! approach! and! the! vocabulary!mapping!tools! used!within!ARIADNE.!The!Getty!AAT! proved!an!appropriate!vocabulary! mapping!hub!that!afforded!a!multilingual!search!capability!in!the!ARIADNE!Portal!via!the!semantic! enrichment! of! partner! subject! metadata! with! derived! AAT! concepts.! The! characteristics! of! the! different!types!of!mappings!of!partner!vocabularies!to!the!Getty!AAT!produced!within!ARIADNE!are! described.! In! total! 6416! mappings! were! conducted,! with! mappings! by! individual! partners! ranging! from!a!few!to!over!1600!terms.!By!December!2016,!concepts!from!27!vocabularies!employed!by!12! project! partners! have! been! mapped! to! the! AAT.! The! vocabulary! mapping! tools! developed! for! ARIADNE!are!available!as!open!source!via!Github.! A! case! study! conducted! an! exploratory! investigation! of! the! semantic! integration! of! extracts! from! archaeological! datasets! with! information! extracted! via! NLP! across! different! languages.! The! investigation!followed!a!broad!theme!relating!to!wooden!material!including!shipwrecks,!with!a!focus! on!types!of!wooden!material,!samples!taken,!wooden!objects!with!dating!from!dendrochronological! analysis,! etc.! The! Demonstrator! developed! for! this! wood/dendrochronological! case! study! is! described!with!illustrative!screendumps;!it!is!available!for!general!use.!The!user!is!shielded!from!the! complexity!of!the!underlying!semantic!framework!(based!on!the!CIDOC!CRM!and!Getty!AAT)!by!the! Web! application! user! interface.! The! Demonstrator! highlights! the! potential! for! archaeological! research!that!can!interrogate!grey!literature!reports!in!conjunction!with!datasets.!Queries!concern! wooden! objects! (e.g.! samples! of! beech! wood! keels),! optionally! from! a! given! date! range,! with! automatic!expansion!over!hierar-chies!of!wood!types.! Lessons*learned* o The!spatial,!temporal!and!subject!dimensions!are!key!to!archaeology!and!the!main!vehicle!for! semantic! linking.! Cleansing! and! normalisation! via! semantic! enrichment! is! necessary! in! each! dimension.! o In!the!subject!dimension,!ARIADNE!requires!high!quality!vocabulary!mappings,!which!cannot!be! achieved! by! automatic! means! alone,! although! appropriate! mapping! tools! can! help.! It! is! important!to!support!expert!intellectual!review!and!provide!contextual!data.!! o The! Getty! AAT! proved! an! appropriate! vocabulary! mapping! hub! that! afforded! a! multilingual! search!capability!in!the!ARIADNE!Portal.! o The!Wood/Dendrochronology!case!study!demonstrated!the!feasibility!of!connecting!information! (at!a! detailed! level)!extracted! from! datasets!and! grey!literature!reports!in!different!languages! and! semantic! cross-searching! of! the! integrated! information.! The! case! study! suggests! that! the! semantic! linking! of! textual! reports! and! datasets! opens! up! possibilities! for! integrative! archaeological!research!across!diverse!resources.! ! ARIADNE!–!D15.3:!Report!on!Semantic!Annotation!and!Linking!Prepared!by!USW! ARIADNE!18!January!2017! ! o Data! cleansing! is! necessary! for! semantic! data! integration! together! with! tools! that! ensure! a! consistent!representation!of!the!extracted!data!in!terms!of!the!semantic!framework.!! o NLP!derived!RDF!statements!do!not!carry!the!same!degree!of!reliability!as!those!derived!from!the! datasets!and!NLP!outcomes!may!include!some!false!positives.!An!indication!of!the!provenance!of! the!RDF!data!should!be!included!in!the!semantic!framework,!which!would!allow!judgments!of!the! reliability!of!the!information.! o The! Wood/Dendrochronology! demonstrator! shows! that! a! Web! application! can! hide! the! complexity! of! the! underlying! semantic! framework! from! the! user! and! allow! querying! and! browsing! the! information! without! expertise! in! SPARQL;! it! illustrates! that! more! intuitive! user! interfaces!are!possible!for!searching!RDF!datasets!than!the!usual!SPARQL!endpoint!or!browsing! hyperlinks.! ! ! ! ! ! ! ARIADNE!–!D15.3:!Report!on!Semantic!Annotation!and!Linking!Prepared!by!USW! ARIADNE!19!January!2017! ! 4 References* AMALGAME,!http://semanticweb.cs.vu.nl/amalgame/!! ARIADNE!(2015)!website:!ARIADNE!at!Linked!Pasts,!http://www.ariadneinfrastructure.eu/News/ARIADNE-at-Linked-Pasts!! Binding!C.!&!Tudhope!D.!(2016):!Improving!Interoperability!using!Vocabulary!Linked!Data.!In:! International!Journal!on!Digital!Libraries,!17(1),!5-21![doi:10.1007/s00799-015-0166-y]! Caracciolo!C.,!Stellato!A.,!Morshed!A.,!Johannsen!G.,!Rajbahndari!S.,!Jaques!Y.!&!Keizer!J.!(2013):!The! AGROVOC!Linked!Dataset.!In:!Semantic!Web.!4(3):!341-348.!! Caracciolo!C.,!Stellato!A.,!Rajbahndari!S.,!Morshed!A.,!Johannsen!G.,!Jaques!Y.!&!Keizer!J.!(2012):! Thesaurus!maintenance,!alignment!and!publication!as!linked!data:!the!AGROVOC!use!case.!In:! International!Journal!of!Metadata,!Semantics!and!Ontologies,!7(1):!65-75.!! Charles!V.,!Freire!N.!&!Isaac!A.!(2014):!!Links,!languages!and!semantics:!linked!data!approaches!in!the! European!Library!and!Europeana.!Proceedings!IFLA!World!Library!and!Information!Congress! 2014,!Lyon,!http://ifla2014-satdata.bnf.fr/pdf/iflalld2014_submission_Charles_Freire_Isaac.pdf!!! CULTUURLINK,!http://cultuurlink.beeldengeluid.nl/app/#/start!! Heritage!Data.!Linked!Data!Vocabularies!for!Cultural!Heritage,!http://www.heritagedata.org!! Isaac!A.,!Waites!W.,!Young!J.!&!Zeng!M.!(eds.)!(2011):!Library!Linked!Data!Incubator!Group:!Datasets,! value!vocabularies,!and!metadata!element!sets![W3C!Incubator!Group!Report,!October!25,! 2011].!http://www.w3.org/2005/Incubator/lld/XGR-lld-vocabdataset/!! ISO!25964-2:2013.!Information!and!documentation!-!Thesauri!and!interoperability!with!other! vocabularies!-!Part!2:!Interoperability!with!other!vocabularies.! http://www.niso.org/schemas/iso25964/#part2!! ISO25964-1:2011.!Information!and!documentation!-!Thesauri!and!interoperability!with!other! vocabularies!-!Part!1:!Thesauri!for!information!retrieval.! http://www.niso.org/schemas/iso25964/#part1!! Kempf!A.,!Neubert!J.,!Faden!M.!(2015):!The!Missing!Link!–!A!Vocabulary!Mapping!Effort!in!Economics.! 14th!European!Networked!Knowledge!Organization!Systems!(NKOS)!Workshop,!TPDL!2015! Poznań.! Liang!A.!&!Sini!M.!(2006):!Mapping!AGROVOC!and!the!Chinese!Agricultural!Thesaurus:!Definitions,! tools,!procedures.!In:!New!Review!of!Hypermedia!and!Multimedia,!12(1):!51-62.! Meghini!C.!et!al.!(forthcoming):!ARIADNE:!A!Research!Infrastructure!for!Archaeology.!In:!Journal!on! Computing!and!Cultural!Heritage.! Miles!A.!&!Bechofer!S.!(2009):!SKOS!Simple!Knowledge!Organization!System!Reference.!W3C! Recommendation,!https://www.w3.org/TR/2009/REC-skos-reference-20090818/#L4138!!! Niccolucci!F.!&!Hermon!S.!(2015):!Representing!gazetteers!and!period!thesauri!in!four-dimensional! spacetime.!In:!International!Journal!on!Digital!Libraries,!17(1):!63-69![doi:10.1007/s00799-0150159-x]! Open!Annotation!Ontology,!http://www.openannotation.org!! OpenRefine,!http://openrefine.org!! ! ARIADNE!–!D15.3:!Report!on!Semantic!Annotation!and!Linking!Prepared!by!USW! ARIADNE!20!January!2017! ! Pelagios,!http://commons.pelagios.org!! PeriodO!client,!http://n2t.net/ark:/99152/p0!! PeriodO!website,!http://perio.do!! PeriodO!(Github),!https://github.com/periodo!! Peripleo,!https://github.com/pelagios/peripleo#peripleo-api!!! Pleiades,!https://pleiades.stoa.org!! Recogito,!http://recogito.pelagios.org!! Richards!J.,!Tudhope!D.!&!Vlachidis!A.!(2015):!Text!Mining!in!Archaeology:!Extracting!Information! from!Archaeological!Reports,!pp.!240-254,!in:!Barcelo!J.!&!Bogdanovic!I.!(eds.):!Mathematics!and! Archaeology.!CRC!Press! SAIM!Instance!Matching!Application,!http://saim.aksw.org!! SENESCHAL!project:!Semantic!ENrichment!Enabling!Sustainability!of!arCHAeological!Links.!University! of!South!Wales,!Hypermedia!Research!Group,! http://hypermedia.research.southwales.ac.uk/kos/seneschal/!! Shaw!R.,!Rabinowitz!A.,!Golden!P.!&!Kansa!E.!(2015):!A!sharing-oriented!design!strategy!for! Networked!Knowledge!Organization!Systems.!International!Journal!on!Libraries,!17(1):!49-61! [doi:10.1007/s00799-015-0164-0]! Shaw!R.,!Rabinowitz!A.,!Golden!P.!&!Kansa!E.!(2015):!Report!on!and!demonstration!of!the!PeriodO! period!gazetteer.!14th!European!Networked!Knowledge!Organization!Systems!(NKOS)! Workshop,!TPDL!2015!Poznań.! SILK!-!Silk!Link!Discovery!Framework,!http://wifo5-03.informatik.uni-mannheim.de/bizer/silk/!! Simon!R.,!Isaksen!L.,!Barker!E.!&!de!Soto!Cañamares!P.!(2016):!Peripleo:!a!Tool!for!Exploring! Heterogenous!Data!through!the!Dimensions!of!Space!and!Time.!In:!Code4Lib!Issue!31,!2016-0128,!http://journal.code4lib.org/articles/11144!! Simon!R.,!Isaksen!L.,!Barker!E.!&!de!Soto!Cañamares!P.!(forthcoming):!The!Pleiades!Gazetteer!and!the! Pelagios!Project,!in:!Berman!M.,!Mostern!R.!&!Southall!H.!(eds.):!Placing!Names:!Enriching!and! Integrating!Gazetteers.!Indiana!University!Press.! SKOS!mapping!relationships,!http://www.w3.org/TR/skos-reference/#L4138!!! SKOS.!Simple!Knowledge!Organization!System.!W3C,!http://www.w3.org/2004/02/skos/!! SPARQL!1.1!Query!Language.!W3C.!(2013),!http://www.w3.org/TR/sparql11-query/!!! Stahn!L.!(2015).!Vocabulary!Alignment!for!archaeological!Knowledge!Organization!Systems.!14th! Workshop!on!Networked!Knowledge!Organization!Systems,!TPDL!2015!Poznań.! STAR!Project:!Semantic!Technologies!for!Archaeological!Resources.!University!of!South!Wales:! Hypermedia!Research!Group,!http://hypermedia.research.southwales.ac.uk/kos/star/!!! STELETO,!http://github.com/cbinding/STELETO/!! STELLAR!Project:!Semantic!Technologies!Enhancing!Links!and!Linked!Data!for!Archaeological! Resources.!University!of!South!Wales:!Hypermedia!Research!Group,! http://hypermedia.research.southwales.ac.uk/kos/STELLAR/!! ! ARIADNE!–!D15.3:!Report!on!Semantic!Annotation!and!Linking!Prepared!by!USW! ARIADNE!21!January!2017! ! Stiller!J.,!Petras!V.,!Gäde!M.!&!Isaac!A.!(2014):!Automatic!Enrichments!with!Controlled!Vocabularies! in!Europeana:!Challenges!and!Consequences,!pp.!238-247,!in:!Digital!Heritage.!Progress!in! Cultural!Heritage:!Documentation,!Preservation,!and!Protection.!Springer!LNCS!8740.!! Zeng!M.!&!Chan!L!(2004):!Trends!and!issues!in!establishing!interoperability!among!knowledge! organization!systems.!In:!Journal!of!American!Society!for!Information!Science!and!Technology,! 55(5):!377-395.!