search

explosion / spaCy

💫 Industrial-strength Natural Language Processing (NLP) in Python
https://spacy.io
MIT License
30.07k stars 4.4k forks source link

Missing documentation on dependency parsing results #657

Closed kristall closed 7 years ago

kristall commented 7 years ago

I used spacy to analyze a short (german) sentence and would like to know more about the used "names"

For example: <--sb--- <-ROOT-- <--oa--- <--cd--- <--cj--- <--oa--- <--svp--

ROOT is the only "clear" one. I checked https://spacy.io/docs/api/annotation but in the given pdf (http://www.mathcs.emory.edu/~choi/doc/clear-dependency-2012.pdf) these abbrevations are not used. Also following the links to ClearNLP only lead to https://emorynlp.github.io/nlp4j/components/dependency-parsing.html which also did not the contain the needed information.

Where can I find a legend of the used abbrevations?

honnibal commented 7 years ago

Ah, damn. This part of the docs needs to be generalised for German...

The German model was trained on the TIGER treebank. I'll find the docs and update the page.

lock[bot] commented 6 years ago

This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.