251 | | ||= Identifier =||= Annotation Tier Description =||= Syntax =||= Examples (without quotes) =|| |
252 | | || `token` || Appropriate tokenisation of resource, i.e. words || String || "Dog", "cat", "walked" || |
253 | | || `lemma` || Lemmatisation of tokens || String || "good", "walking", "dog" || |
254 | | || `pos` || Part-of-Speech annotations || [#REF_UD_POS Universal POS tags] || "NOUN", "VERB", "ADJ" || |
255 | | || `orth` || Orthographic transcription of (mostly) spoken resources || String || "dug", "cat", "wolking" || |
256 | | || `norm` || Orthographic normalization of (mostly) spoken resources || String || "dog", "cat", "walking" || |
257 | | || `phonetic` || Phonetic transcription || [#REF_SAMPA Speech Assessment Methods Phonetic Alphabet (SAM-PA)] || "'du:", "'vi:-d6 'ha:-b@n" || |
258 | | || `ne` || Named entities || String || "Utrecht", "Poland", "Felix the Cat" || |
259 | | || `text` || Annotation tier that is used in [#basicSearch Basic Search] || String || "Dog", "cat" "walked" || |
| 252 | ||=Identifier =||=Annotation Tier Description =||=Syntax =||=Examples (without quotes) =|| |
| 253 | || `token` || Appropriate tokenisation of resource, i.e. words || ''String'' || "Dog", "cat", "walked" || |
| 254 | || `lemma` || Lemmatisation of tokens || ''String'' || "good", "walking", "dog" || |
| 255 | || `pos` || Part-of-Speech annotations || [#REF_UD_POS Universal POS tags] || "NOUN", "VERB", "ADJ" || |
| 256 | || `orth` || Orthographic transcription of (mostly) spoken resources || ''String'' || "dug", "cat", "wolking" || |
| 257 | || `norm` || Orthographic normalization of (mostly) spoken resources || ''String'' || "dog", "cat", "walking" || |
| 258 | || `phonetic` || Phonetic transcription || [#REF_SAMPA SAMPA] || "'du:", "'vi:-d6 'ha:-b@n" || |
| 259 | || `names` || Named entities || ''String'' || "Utrecht", "Poland", "Felix the Cat" || |
| 260 | || `text` || Annotation tier that is used in [#basicSearch Basic Search] || ''String'' || "Dog", "cat" "walked" || |
| 261 | |
| 262 | The column Syntax describes the inventory of symbols that a Client `MUST` use with a corresponding annotation layer; the value ''String'' denotes that symbols are arbitrary Unicode Strings, i.e. no fixed inventory of symbols are defined. |