parse annotations using a model

[thatbudakguy]

parse annotations using a model

[thatbudakguy]

this might be a better fit for spacy's new SpanCategorizer. maybe we can use this example project and some smart pre-annotating to bootstrap a model for parsing annotations. we could extract:

• fanqie, e.g. AB反
• yin, e.g. 音X
• qualifiers, e.g. ...下同, ...注同,
• notes about textual variation, e.g. 本又作..., 本亦作..., [work]作...
• the mystery 如字
• references to other commentaries using 云
• conjunctions, e.g. ...或..., ...又...
• semantic indicators, e.g. X也 and AB之[A|B]
• citations with numbers, e.g. 凡三篇正二攝一
• 卦?
• 徐?

[thatbudakguy]

approach is now outlined in docs/pipeline.md; closing in favor of more specific tickets.