diff --git a/convert-anystyle-data/schema/gold_standard.xml b/convert-anystyle-data/schema/gold_standard.xml index bbc89c4fa9b08befd7036479ec4f1a183622132e..56eb418d60117e658627a4e4ca58e35b0242d3fc 100644 --- a/convert-anystyle-data/schema/gold_standard.xml +++ b/convert-anystyle-data/schema/gold_standard.xml @@ -28,7 +28,7 @@ </seg> <bibl>A. Dicey, Can English Law be taught at the Universities? (1883) 20.</bibl> </output> - <output type="bibl"> + <output type="bibl" xmlns="http://www.tei-c.org/ns/1.0"> <!-- 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. @@ -37,7 +37,7 @@ in fact, I am looking for a way to encode "no-following-whitespace" but haven't found one yet). --> <p type="footnote"> <seg type="footnote-marker">3</seg> - <bibl xmlns="http://www.tei-c.org/ns/1.0"> + <bibl> <seg type="signal">See</seg> <author> <persName> @@ -56,7 +56,7 @@ <biblScope unit="page" from="at">at 171</biblScope> . </bibl> - <bibl xmlns="http://www.tei-c.org/ns/1.0"> + <bibl> <!-- From the context, it is clear that the following comment is connected to this reference, however, this could only be inferred by a LLM. Normal ML-models could be trained to predict that it is a non-bibliographic section and discard it. --> @@ -80,12 +80,12 @@ </bibl> </p> </output> - <output type="biblStruct"> + <output type="biblStruct" xmlns="http://www.tei-c.org/ns/1.0"> <!-- This output contains pure bibliographic metadata with all non-relevant information removed, using top-level TEI <biblStruct> elements. This data can then be further translated into other bibliographic data exchange formats (such as MODS, RIS, BibTeX, etc.). The information is generated from the <bibl> data above. --> - <biblStruct xmlns="http://www.tei-c.org/ns/1.0" n="2"> + <biblStruct n="2"> <analytic> <title level="a">The Search for Principle</title> <author> @@ -104,7 +104,7 @@ <biblScope unit="page" from="at">at 171</biblScope> </monogr> </biblStruct> - <biblStruct xmlns="http://www.tei-c.org/ns/1.0" n="3"> + <biblStruct n="3"> <monogr> <author> <persName>