Cultural Heritage Language Technologies

1
Cultural Heritage Language Technologies

• ??G?S?? S?? ??T???
• ??F????S ??????T???S
• S?? ???µ???
• ?pe?????? ?a????t??
• ?ap?d???? Sa???t??
• ???ßa?? ???e???? ?2001073

2
Cultural Heritage Language Technologies

• ??a p????aµµa s??e??as?a? ??a ?a d?µ??????????
  ?p?????st??? e??a?e?a ??a t? µe??t? t?? a??a???
  e????????, ?at??????, ?a? t?? pa?a??? ???ß??????
  ?e?µ???? ??a t? d??t?? t?? s?µßeß??µ???? ??f?a???
  ß?ß????????.
• ? ???µat?d?t?s? t?? ????? pa???eta? ap? t?
  National Science Foundation ?a? t? European
  Union International Digital Library Collaborative
  Research Program

3
?? st???? t?? p?????µµat??

• T??e? ?a p??sa?µ?se? t?? a?a?a???e?? ap? t? ped??
  t?? ?p?????st???? ???ss?????a?, t?? a???t?s?? ?a?
  t?? ape?????s?? p????f????? se t??p??? p??
  s?ed?????ta? s???e???µ??a ??a ?a ß????s??? t???
  f??t?t?? ?a? t??? µe?et?t?? t?? ??as????
  ep?st?µ?? ?a p?????s??? t?? e??as?a t???.
• ?p?s??pe? ?a ?esp?se? ??a d?e???? p?a?s?? µe
  a????t? p??t?pa ??a t? µa???p???esµ? s??t???s?,
  t? d?a??µ? ?a? t? d?a?e?t???????t?ta t??
  µetaded?µ???? µeta?? t?? s??dedeµ???? ??f?a???
  ß?ß????????.
• ?a e?a?e?f???? ?? d?s????e? a?????s?? sta
  e???????, ?at?????, ?a? pa?a?? ???ß????? ?e?µe?a
  st?? a?????? ???sse? t???.

4
?as??? te???????a

• ? ßas??? te???????a t?? ??f?a??? ß?ß????????
  pa???eta? se ????? t??? s??e???te? ap? t?
  ß?ß??????? Perseus. ?? s?st?µa Perseus pa???e?
  ??a ?e???? pe??ß????? p?? µp??e? ?a p??e?
  ?p???d?p?te SGML ? ??d???p???µ??? XML ?e?µe?? ?a?
  ?a t? pa???s??se? st? t???? st??? ???ste? µe HTML
  ? ???e? µ??f?? ?p?? PDF.
• - ??t? t? s?st?µa DL pa?ad?de? 8.5
  e?at?µµ???a
• se??de? t? µ??a µ?s? web.
• ? s?ed?asµ?? t?? s?st?µat?? ep?t??pe? st?? ??e?
  efa?µ???? ?a µp????? e????a ?a e?s?µat????? st??
  ?p?????sa a???te?t????? d?µ?.

5
????µ??

• ???????? ?a? ?at????? ?e?µe?a ap? Perseus (6
  e?at?µµ???a ???e?? e????????, 4 e?at?µµ???a
  ???e?? ?at??????, µe t?? a?t?st???e? a???????
  µetaf??se??)
• ???as?e? t?? Issac Newton ap? t? Newton Project
  t?? Imperial College
• ?at????? ?e?µe?a ap? t? Stoa Consortium t??
  University of Kentucky
• ?a?a?? ?e?µe?a ???ß???? ap? t? University of
  California ?a? t?? Arnamagnaean Institute
• ?e?µe?a ap? t?? ????µ?d? Project (DL ??a t??
  ?st???a t?? µ??a?????)

6
S??e???s?µ? ?p?d?µ?

• Se a?t? t? p????aµµa, d?µ?????????e µ?a ?p?d?µ?
  ??a t? s??e??as?a µeta?? t?? s?st?µ?t??
  ????sµ???? p?? ßas????ta? st? Open Archives
  Initiative protocols ??a ?a ?????? t??
  d?af??et???? s??????? ap? d??f??e? ??f?a???
  ß?ß??????e? ?a ?e?t?????s??? µa?? t?s? e????a ?s?
  ta ?e?µe?a µ?sa se µ?a e??a?a ß?ß???????.
• ???te??eta? t? p??t?????? OAI ??a ?a µ???ast???
  ??? µ??? ta ßas??? Dublin Core µetaded?µ??a, a???
  ?a? ta p?? ?ept?µe?? µetaded?µ??a p??
  ???s?µ?p?????ta? sta s?st?µata ??f?a???
  ß?ß????????, ?p?? pe?????? ?a? s????a.

7
Parsers

• ? ep??tas? ? ? a??pt??? t?? µ??f????????
  e??a?e??? a????s?? ??a ta e???????, ta ?at?????
  ?a? pa?a?? ???ß????? e??a? ?eµe???d?? ??a a?t??
  t?? efa?µ????.
• - ?? ap??? p???p?????se? te??????
  de? e??a? a??et? a???ße??.
• ?? p????aµµa Perseus ?a pa??s?e? ??a? Parser ??a
  ??ass??? e??????? ?a? ?at?????.
• ?? Istituto Di Linguistica Computazionale del
  CNR, ???a ?a a?apt??e? ??a s?st?µa ??a ta
  ?at?????.
• ?? pa?ep?st?µ?? ?a??f????a? ?a? t? ?d??µa
  Arnamagnaean ?a? ?a d?µ??????se? ??a? Parser ??a
  t??? pa?a?? ???ß?????.
• ???µa, µet? ta a????? s??d?a ?a d?µ???????e? ??a?
  Parser ??a pa?a?? a??????.

8
????t?s? p??????ss?? p????f?????

• ? p??????ss? a???t?s? p????f????? µp??e? ?a e??a?
  e?a??et??? ???s?µ? ??a t??? µ? e?e?d??e?µ?????
  µe?et?t?? ?a? t??? sp??dast?? p?? ?????? ???a
  e???????, ?at?????, ? pa?a?? ???ß?????, a??? de?
  e??a? ??a??? ?a d?at?p?s??? e??t?se?? st?? a?????
  ???ssa.
• ?? ?????p?? p?? µe?et??? ?µ???, pa?ade??µat??
  ?????, ?a µp????sa? ?a e?d?af????ta? p??? ??a t??
  ?????a t?? ??????? f?µ??, t?? ?ste??f?µ?a? ?a?
  t?? ?p?????? p?? d?ad?aµat??e? p??? s?µa?t???
  ???? st?? ????da.
• ??a? st???? t?? p?????µµat?? e??a? ?a a?apt??????
  ?????? µ??f?? e??et???as?? a?t?? t?? ???ss??.

9
?pe?????s? p????f?????

• ???? s?et??? µe ta e??a?e?a ??a t?? a???t?s?
  p??????ss?? p????f????? e??a? ?? d??at?t?te? ??a
  t?? ape?????s? p????f?????.
• ?a ap?te??sµata a?a??t?s?? pa???s?????ta? p???
  s???? se ??a? ?at????? p?? e??a? ta????µ?µ???? µe
  t??p? p?? e??a? d?s???t?? ??a t?? te???? ???st?.
• ?p?µ???? t? s?st?µa p????aµµat?st??e ?a a?apt??e?
  ??a s?st?µa p??
• Ø p??sd?????e? a?t?µata t?? ???e?? ??e?d??,
• Ø t?? ta????µe? se ?µ?de?,
• Ø ???µ??e? e?e??e? t?? ?µ?de? a?a?????
• Ø ape??????e? ?a? ep?t??pe? st? ???st? ?a st?afe?
  se ?p?t?µe?? se s???e???µ??? ?e?µe?? se µ?a
  a?a??t?s?.

10
S??ta?t??? e??a?e?a a????s??

• ???sd????sµ?? t?? s??ta??? t?? ??µ?t??
• ? s??ta?? ?a? ? ???s? s???e???µ???? ???e?? µp??e?
  ?a pa?ap?µp??? se ??a ?f??, ??a? s??t??t?, ?
  a??µa ?a? se ?e?µe??.
• ??a a?t? ß?ßa?a e??a? d?s???a ??a t? ???? ?t? ?
  p???p????t?ta a?t?? t?? ???ss?? e??a? µe????.

11
????????s? t?? e?d???? ???s??

• ??? ?? a?t?µate? d?ad??as?e? µp????? ?a pa??????
  p????? ???s?µe? p????f???e?, ?? µe?et?t?? ?a
  ?e??s??? ?a d?????s???, ?a s?????s???, ?a? ?a
  epe?te????? ta a?t?µata ap?te??sµata
• ? s?????sµ??? p?a?t??? ??a t??? µe?et?t?? e??a?
  ?a t?p????? ta ap?te??sµata ?a? st? s????e?a ?a
  p??s??s??? ta s????a t???, t?? s?µe??se?? t???
  ?e?????afa.
• S a?t? t? p????aµµa ????? ?? st??? ?a
  d?µ??????s??? ??a? µ??a??sµ? ??a ?a ?????ta?
  ape??e?a? ?? s?µe??se?? t?? µe?et?t?? ?a? ?a
  ap????e???ta?.
• Ta d?µ???????e? ??a p??t?p???a?? e??a?e?? ??a t??
  DL.

12
S?µp??asµa

• ??µ?????????a? e??a?e?a p?? d?e????????? t??
  a?????s? a?t?? t?? ?e?µ????, µe a?t?? t?? t??p?,
  t?? ?a??st??? e?????te?? ??a ta µe???a ?e????
  a???at???a.
• ??µ?????????a? ep?s?? e??a?e?a p?? ep?t??p???
  st??? sp??dast?? ?a? t??? µe?et?t?? ?a ??t?s???
  ?a? ?a apa?t?s??? se e??t?se?? ??a t? ???ss???
  ???s? p?? ?a ?ta? d?s???? ? ad??at? ?a apa?t??e?
  ??? ap? ??a ??e?t?????? pe??ß?????.

13
S?µp??asµa

• ? ???µat?d?t?s? ap? a?t?? t?? ep???????s?
  ep?t??pe? ?a p?a?µat?p????e? t? ??aµa d?? ????
  µ??t???? t?? s??e??as?a?. ??t? ta µ??t??a e??a?
• Ø ??a d??t?? ?????? st???e??? s?µpe??f???? µ?s?
  t?? OAI sta p??? ?aµ??? ep?peda p??a ap? ta
  µetaded?µ??a,
• Ø ?a? ??a µ??t??? ?p?? ? e?d??? ???s? t?? ???st??
  µp??e? ?a s?µß??e? ?a? ?a ße?t??se? ta e??a?e?a
  µ?sa se µ?a ??f?a?? ß?ß???????.