8.1.10. cltk.morphology package¶

8.1.10.1. Submodules¶

8.1.10.2. cltk.morphology.akk module¶

Functions and classes for Akkadian morphology.

cltk.morphology.akk.get_bound_form(noun, gender)[source]¶

Return bound form of nound, given its gender.

>>> get_bound_form("awīlum", "m")
'awīl'

Return type:: str

cltk.morphology.akk.decline_noun(noun, gender, mimation=True)[source]¶

Return a list of all possible Akkadiandeclined forms given any form

of a noun and its gender.

>>> decline_noun('iltum', 'f')
[('iltum', {'case': 'nominative', 'number': 'singular'}), ('iltam', {'case': 'accusative', 'number': 'singular'}), ('iltim', {'case': 'genitive', 'number': 'singular'}), ('iltān', {'case': 'nominative', 'number': 'dual'}), ('iltīn', {'case': 'oblique', 'number': 'dual'}), ('ilātum', {'case': 'nominative', 'number': 'plural'}), ('ilātim', {'case': 'oblique', 'number': 'plural'})]

Return type:: List[Tuple[str, Dict[str, str]]]

8.1.10.3. cltk.morphology.lat module¶

This modules provides Decliner for Latin. Given a lemma, the Decliner will provide each grammatically valid forms

This work is based on the lexical and linguistic data built for and by the Collatinus Team ( https://github.com/biblissima/collatinus ). This module hence inherit the license from the original project. The objective of this module is to port part of Collatinus to CLTK.

class cltk.morphology.lat.CollatinusDecliner[source]¶

Bases: object

Latin Decliner based on Collatinus data and approach to declining words for Latin

# Ensure you have downloaded the corpus latin_models_cltk before running this
from cltk.stem.lat.declension import CollatinusDecliner

decliner = CollatinusDecliner()
print(decliner.decline("via"))

 [
     ('via', '--s----n-'), ('via', '--s----v-'), ('viam', '--s----a-'), ('viae', '--s----g-'),
     ('viae', '--s----d-'), ('via', '--s----b-'), ('viae', '--p----n-'), ('viae', '--p----v-'),
     ('vias', '--p----a-'), ('viarum', '--p----g-'), ('viis', '--p----d-'), ('viis', '--p----b-')
 ]

_remove_disambiguation(root)[source]¶

Remove disambiguation index from lemma root

Parameters:: root – Root in Collatinus
Returns:: Cleaned root

_getRoots(lemma, model)[source]¶

Retrieve the known roots of a lemma

Parameters:

lemma (str) – Canonical form of the word (lemma)
model (dict) – Model data from the loaded self.__data__. Can be passed by decline()

Returns:

Dictionary of roots with their root identifier as key

Return type:

dict

decline(lemma, flatten=False, collatinus_dict=False)[source]¶

Decline a lemma

Warning

POS are incomplete as we do not detect the type outside of verbs, participle and adjective.

Raises:

CLTKException – When the lemma is unknown to our data

Parameters:

lemma (str) – Lemma (Canonical form) to decline
flatten (bool) – If set to True, returns a list of forms without natural language information about them
collatinus_dict (bool) – If sets to True, Dictionary of grammatically valid forms, including variants, with keys corresponding to morpho informations.

Returns:

List of tuple where first value is the form and second the pos, ie [(“sum”, “v1ppip—“)]

Return type:

list or dict

property lemmas: Dict[str, Dict[str, str]]¶

Return type:: Dict[str, Dict[str, str]]

8.1.10.4. cltk.morphology.morphosyntax module¶

A module for representing universal morphosyntactic feature bundles.

class cltk.morphology.morphosyntax.MorphosyntacticFeatureBundle(*features)[source]¶

Bases: object

A representation of a set of features, usually associated with a word form.

all()[source]¶

Return type:: List[Tuple[Type[MorphosyntacticFeature], List[MorphosyntacticFeature]]]

underspecify(feature_name)[source]¶

Underspecify the given feature in the bundle. >>> f1 = f(F.pos, N.pos, V.neg) >>> f1.underspecify(F) >>> f1[F] is Underspecified True

Return type:: None

matches(other)[source]¶

This feature bundle matches other if other contains all the features of this bundle, i.e. if this bundle is an improper subset of other. Underspecified features will match.

>>> f1 = f(F, N.pos, V.neg)
>>> f2 = f(F.neg, N.pos, V.neg)
>>> f3 = f(F.pos, N.neg, V.pos)
>>> f1.matches(f2)
True
>>> f1.matches(f3)
False

Return type:: bool

keys()[source]¶

values()[source]¶

items()[source]¶

cltk.morphology.morphosyntax.f¶: alias of MorphosyntacticFeatureBundle

cltk.morphology.morphosyntax.to_categorial(pos)[source]¶

Maps UD parts of speech to binary categorial feature bundles. In some cases these are underspecified, including empty bundles for interjections. >>> to_categorial(POS.adjective) {F: [neg], N: [pos], V: [pos]} >>> to_categorial(POS.particle) {F: [pos]} >>> to_categorial(POS.interjection) {}

Return type:: MorphosyntacticFeatureBundle

cltk.morphology.morphosyntax.from_ud(feature_name, feature_value)[source]¶

For a given Universal Dependencies feature name and value, return the appropriate feature class/value. >>> from_ud(‘Case’, ‘Abl’) ablative >>> from_ud(‘Abbr’, ‘Yes’) pos >>> from_ud(‘PronType’, ‘Ind’) indefinite

Return type:: Optional[MorphosyntacticFeature]

8.1.10.5. cltk.morphology.universal_dependencies_features module¶

Data types for each morphological category and features annotated by the Universal Dependencies (UD) project (<https://universaldependencies.org/guidelines.html>_).

These are from v2 of UD, except for Strength which is from v1 and was (as of 12/2020) still in the Gothic treebank.

class cltk.morphology.universal_dependencies_features.MorphosyntacticFeature(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]¶

Bases: CLTKEnum

A generic multivalued morphosyntactic feature.

class cltk.morphology.universal_dependencies_features.N(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]¶