• Back to Russian-GSD page

    • Token Distribution across Case

    The following histogram captures the token distribution per different part-of-speech (POS) tags.

    Legend on the top-right shows the different values the Case attribute takes.
    'NA' denotes those tokens which do not possess the Case attribute.

    Case

    Token examples for each POS:

     NOUN       PUNCT       ADJ       ADP       VERB       PROPN       CCONJ       ADV       NUM       PRON       DET       X       PART       AUX       SCONJ       SYM      

    Case agreement rules:

    The following decision tree visualizes the rules used for classifying presence/absence of morphological agreement between two tokens that are connected by a dependency relation denoted by relation. head-pos and child-pos refer to the POS tag of the head and child token respectively.

    Each node of the tree represents a portion of the data. samples denotes the number of training data points in that node. value is the class distribution within that node. Each edge denotes the feature used for splitting.
    Leaf nodes contain the description of all of the features that appear in that leaf. * denotes that the feature can take any value.

    Tree for p=0.01

    Click on to show summary of agreement rules.

    1. NOUN tokens agree when the dependent token belongs to [ADJ] for the dependency relations: modifer(mod)

    2. NOUN tokens agree with their head for the dependency relations: conjunct(conj)

    3. PROPN tokens agree with their head for the dependency relations: appositional modifier(appos), flat multiword expression(flat@name), flat multiword expression(flat@foreign), unk(unk), vocative(vocative)

    4. DET tokens agree with their head for the dependency relations: determiner(det)

    5. All tokens agree with their head tokens for the dependency relations: subject (subj), list (list), subject (subj@pass), parataxis (parataxis)

    6. ADJ tokens agree when the dependent token belongs to [NOUN] for the dependency relations: oblique complements(comp:obl@agent), flat multiword expression(flat)

    7. NUM tokens agree with their head for the dependency relations: goes with(goeswith), modifer(mod@gov), compound(compound), modifer(mod@entity)

    8. DET tokens agree when the dependent token belongs to [NOUN] for the dependency relations: direct object complements(comp:obj), unk@fixed(unk@fixed)

    9. VERB tokens agree with their head for the dependency relations: modifer(mod@relcl), predicative complements(comp:pred)

    10. VERB tokens agree when the dependent token belongs to [ADJ] for the dependency relations: underspecified dependency(udep)

    11. NOUN tokens agree when the dependent token belongs to [NOUN] for the dependency relations: orphan(orphan)

    Case

    Examples for each leaf node:

     Leaf-0       Leaf-1       Leaf-2       Leaf-3       Leaf-4       Leaf-5       Leaf-6       Leaf-7       Leaf-8       Leaf-9       Leaf-10       Leaf-11       Leaf-12       Leaf-13       Leaf-14       Leaf-15       Leaf-16       Leaf-17      

    Click on to expand the tree.