• Back to Russian-Taiga page

    • Token Distribution across Number

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

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

    Number

    Token examples for each POS:

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

    Number 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. ADJ tokens agree with their head for the dependency relations: predicative complements(comp:pred), complement for auxiliary(comp:aux), list(list), modifer(mod)

    2. NOUN tokens agree with their head for the dependency relations: subject(subj)

    3. VERB tokens agree with their head for the dependency relations: modifer(mod@relcl), complement for auxiliary(comp:aux@pass), conjunct(conj), flat multiword expression(flat)

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

    5. PROPN tokens agree with their head for the dependency relations: appositional modifier(appos), goes with(goeswith), oblique complements(comp:obl@agent), flat multiword expression(flat@name), vocative(vocative)

    6. PRON tokens agree with their head for the dependency relations: subject(subj@pass), orphan(orphan), overridden disfluency(reparandum), underspecified dependency(udep)

    7. All tokens agree with their head tokens for the dependency relations: unk@fixed (unk@fixed)

    8. NUM tokens agree with their head for the dependency relations: modifer(mod@gov)

    9. PRON,PROPN tokens agree with their head for the dependency relations: dislocated elements(dislocated)

    Number

    Examples for each leaf node:

     Leaf-0       Leaf-1       Leaf-2       Leaf-3       Leaf-4      

    Click on to expand the tree.