diff --git a/convert-anystyle-data/schema/gold_standard.xml b/convert-anystyle-data/schema/gold_standard.xml index 575544acc66559fffca8b8e5066514e76727e77a..e5af45782a4c61f3705918069717ff420471b94b 100644 --- a/convert-anystyle-data/schema/gold_standard.xml +++ b/convert-anystyle-data/schema/gold_standard.xml @@ -1,13 +1,17 @@ <dataset> <instance source="doi:10.1111/1467-6478.00080"> - <input> + <input type="formatted"> <!-- This is the data from which the output data is predicted by the model/algorithm --> <!-- Alternative tag names: <feature>, <predictor> --> + <!-- This input type is for human consumption, for ease of reading etc. --> 3 See R. Goff, ‘The Search for Principle’ (1983) Proceeedings of the British Academy 169, at 171. This is an amplification of Dicey’s remark that ‘[b]y adequate study and careful thought whole departments of law can . . . be reduced to order and exhibited under the form of a few principles which sum up the effect of a hundred cases . . .’. A. Dicey, Can English Law be taught at the Universities? (1883) 20. </input> + <input type="raw"> + <!-- the unformatted raw reference utf-8 encoded string, meant for processing --> + <![CDATA[3 See R. Goff, ‘The Search for Principle’ (1983) Proceeedings of the British Academy 169, at 171. This is an amplification of Dicey’s remark that ‘[b]y adequate study and careful thought whole departments of law can . . . be reduced to order and exhibited under the form of a few principles which sum up the effect of a hundred cases . . .’. A. Dicey, Can English Law be taught at the Universities? (1883) 20.]]></input> <output type="references"> <!-- alternative tag names: <target> <label> --> <!-- This output type simply segments the input into parts which contain bibliographic data and those which do not. @@ -30,7 +34,7 @@ <bibl>A. Dicey, Can English Law be taught at the Universities? (1883) 20.</bibl> </p> </output> - <output type="bibl" > + <output type="bibl"> <!-- This output contains the input text annotated according to the TEI rules on bibliographic references, using top-level <bibl> elements and those allowed within them. The data usually comes from human annotators and might contain errors and inconsistencies, but should be valid TEI. The annotation should be lossless, i.e.