daelba commited on
Commit
55bd5a0
1 Parent(s): 27044a9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +49 -3
README.md CHANGED
@@ -1,3 +1,49 @@
1
- ---
2
- license: cc-by-nc-sa-4.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ language:
4
+ - cs
5
+ - de
6
+ pipeline_tag: text2text-generation
7
+ tags:
8
+ - code
9
+ - wikibase
10
+ - vital records
11
+ base_model: google/mt5-small
12
+ inference:
13
+ parameters:
14
+ max_new_tokens: 100
15
+ ---
16
+
17
+ A model for connverting vital records to Wikibase. Trained on a transcription dataset obrained with HTR (<a href="https://gitlab.com/scripta/escriptorium">eScriptorium</a>) from 150 pages of the Jewish registry book <a href="https://vademecum.nacr.cz/vademecum/permalink?xid=8c9e996c-e65c-41a0-8cbc-f8fc8dc32468">HBMa 2501</a> (<a href="https://www.wikidata.org/wiki/Q108724909">Wikidata</a>). The dataset contains 1071 vital records, which were uploaded to <a href="https://matrika.wikibase.cloud">Wikibase Cloud</a> after processing using this model.
18
+
19
+ Based on <a href="https://huggingface.co/google/mt5-small">Google's mT5</a>.
20
+
21
+ <h3>Processing ditto marks</h3>
22
+
23
+ <pre>
24
+ mt5prefix = "dto"
25
+ upperCell = "18 Juny 1858 H. Barb. Kohn"
26
+ lowerCell = "dto dto H. Ros. Plowitz"
27
+ dataset_input = f"{mt5prefix}:{upperCell}|{lowerCell}"
28
+ dataset_target = "18 Juny 1858 H. Ros. Plowitz"
29
+ </pre>
30
+
31
+ <h3>Processing a table cell</h3>
32
+
33
+ <pre>
34
+ mt5prefix = "wbPre"
35
+ header = "Namen des Vaters mit Anführung des Standes, ob Familiant od. Gewerbsmann, u. seines Wohnortes, Schutzdom. Haus-Nr. und bei ehelichen Geburten seines Gubernial-Ehekonsenses Datum und Zahl"
36
+ cell = "Markus Gibianer, Lederhändler, S. d. Seligmann Gibianer u. der Magdalena geb. Motz"
37
+ dataset_input = f"{mt5prefix}:{header}|{cell}"
38
+ dataset_target = "[[<a href="https://matrika.wikibase.cloud/wiki/Property:P23">P23</a>:Markus Gibianer|<a href="https://matrika.wikibase.cloud/wiki/Property:P26">P26</a>:Lederhändler]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P27">P27</a>:Seligmann Gibianer]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P28">P28</a>:Magdalena Gibianer geb. Motz]]"
39
+ </pre>
40
+
41
+ <h3>Processing a whole record</h3>
42
+
43
+ <pre>
44
+ mt5prefix = "wbDef"
45
+ input_string = "[[<a href="https://matrika.wikibase.cloud/wiki/Property:P5">P5</a>:60]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P6">P6</a>:1865-05-05]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P7">P7</a>:H. Charlotte Löw]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P12">P12</a>|DD:23]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P12">P12</a>|MM:04]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P12">P12</a>|YY:1865]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P14">P14</a>|<a href="https://matrika.wikibase.cloud/wiki/Property:P8">P8</a>:1061/2]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P14">P14</a>:<a href="https://matrika.wikibase.cloud/wiki/Item:Q8">Q8</a>]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P15">P15</a>|DD:06]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P15">P15</a>|MM:05]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P15">P15</a>|YY:1865]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P16">P16</a>:<a href="https://matrika.wikibase.cloud/wiki/Item:Q22">Q22</a>]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P17">P17</a>:Friederika]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P20">P20</a>:4]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P21">P21</a>:<a href="https://matrika.wikibase.cloud/wiki/Item:Q13">Q13</a>]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P22">P22</a>:<a href="https://matrika.wikibase.cloud/wiki/Item:Q15">Q15</a>]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P23">P23</a>:Jakob Raubitschek|<a href="https://matrika.wikibase.cloud/wiki/Property:P26">P26</a>:Eisenhändler]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P27">P27</a>:Josef Raubitschek]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P28">P28</a>:Theresia Raubitschek geb. Latus]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P24">P24</a>:Pauline XXX]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P29">P29</a>:Markus Raudnitz]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P30">P30</a>:Rachel Raudnitz geb. Kuh]]"
46
+ dataset_input = f"{mt5prefix}:{input_string}"
47
+ dataset_target = "[[<a href="https://matrika.wikibase.cloud/wiki/Property:P10">P10</a>:<a href="https://matrika.wikibase.cloud/wiki/Item:Q5">Q5</a>]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P12">P12</a>:1865-04-23]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P14">P14</a>:<a href="https://matrika.wikibase.cloud/wiki/Item:Q8">Q8</a>|<a href="https://matrika.wikibase.cloud/wiki/Property:P8">P8</a>:1061/2]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P15">P15</a>:1865-05-06]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P16">P16</a>:<a href="https://matrika.wikibase.cloud/wiki/Item:Q22">Q22</a>]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P17">P17</a>:Friederika]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P18">P18</a>:Raubitschek]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P19">P19</a>:Friederika Raubitschek]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P1">P1</a>:<a href="https://matrika.wikibase.cloud/wiki/Item:Q1">Q1</a>]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P20">P20</a>:4]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P21">P21</a>:<a href="https://matrika.wikibase.cloud/wiki/Item:Q13">Q13</a>]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P22">P22</a>:<a href="https://matrika.wikibase.cloud/wiki/Item:Q15">Q15</a>]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P23">P23</a>:Jakob Raubitschek|<a href="https://matrika.wikibase.cloud/wiki/Property:P26">P26</a>:Eisenhändler]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P24">P24</a>:Pauline Raubitschek]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P27">P27</a>:Josef Raubitschek]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P28">P28</a>:Theresia Raubitschek geb. Latus]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P29">P29</a>:Markus Raudnitz]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P30">P30</a>:Rachel Raudnitz geb. Kuh]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P33">P33</a>:Charlotte Löw]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P38">P38</a>:<a href="https://matrika.wikibase.cloud/wiki/Item:Q170">Q170</a>]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P5">P5</a>:60]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P6">P6</a>:1865-05-05]] [[<a href="https://matrika.wikibase.cloud/wiki/Property:P7">P7</a>:H. Charlotte Löw]]"
48
+ </pre>
49
+