Create_penntree_feature_for_TF
Create penntree feature for Text-Fabric
This repository contains the Jupyter Notebook used to create three new Text-Fabric feature:
- pentree: Penn tree like syntax tree.
The final feature files will be added to the package available at the tonyjurg/N1904addons repository.
Example
The following example shows a penn tree generated when passing the feature data to nltk:
from nltk import Tree
ptbString=F.penntree.v(sentenceNode)
tree = Tree.fromstring(ptbString)
tree.pretty_print() # console-style print
S
|
WG
___________________________________|_________________
CL |
_______|________________ |
| NP-SBJ |
| ________________|_____________ |
| | | CL |
| | | _____________|____ |
VP-V | | VP-V PP-ADV CL
| | | | _________|______ ____|____________
VERB NOUN PUNCT VERB PREP NOUN PUNCT NOUN PRON NOUN PUNCT
| | | | | | | | | | |
ἐγένετο ἄνθρωπος , ἀπεσταλμένος παρὰ θεοῦ , ὄνομα αὐτῷ ἰωάνης ·
Production notebook
You can view the production notebook on nbviewer.org.
Alternative, you can also download it from the GitHub repository.
Attribution and footnotes
The following resources were consulted for creating the notebook:
- Penn Treebank Tag Guidelines PDF
- NLP @ Univ. of Pennsylvania (note: the original homepage of the Penntree bank project is gone.)
- Building a Large Annotated Corpus of English: The Penn Treebank
- The Penn treebank: an overview
The Greek base text is from Nestle1904 Greek New Testament, edited by Eberhard Nestle, published in 1904 by the British and Foreign Bible Society:
Nestle, Eberhard. Η Καινή Διαθήκη Novum Testamentum Graece (New York: Fleming H. Revell Company, 1904). The 1913 reprint is available here, which was transcribed by Diego Santos. All this material is in Public domain.
The N1904-TF dataset available under MIT license. Formal reference:
Tony Jurg, Saulo de Oliveira Cantanhêde, & Oliver Glanz. (2024). CenterBLC/N1904: Nestle 1904 Text-Fabric data. Zenodo. DOI: 10.5281/zenodo.13117911.
License
This notebook is released under the Creative Commons Attribution 4.0 International (CC BY 4.0)
Citation
If you use this repository in your academic work, please cite it.