• Back to Marathi-UFAL page

    • Token Distribution across Gender

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

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

    Gender

    Token examples for each POS:

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

    Gender 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. All tokens agree with their head tokens for the dependency relations: subject (subj), vocative (vocative)

    2. NOUN tokens agree when the dependent token belongs to [ADP] for the dependency relations: underspecified dependency(udep@poss)

    3. VERB tokens agree when the dependent token belongs to [NOUN] for the dependency relations: underspecified dependency(udep), oblique complements(comp:obl), compound(compound@lvc), direct object complements(comp:obj), discourse element(discourse)

    4. NOUN tokens agree when the dependent token belongs to [DET] for the dependency relations: determiner(det)

    5. NOUN tokens agree when the dependent token belongs to [ADJ] for the dependency relations: appositional modifier(appos), modifer(mod)

    6. VERB tokens agree when the dependent token belongs to [VERB] for the dependency relations: complement for auxiliary(comp:aux@pass), conjunct(conj)

    7. AUX tokens agree when the dependent token belongs to [VERB] for the dependency relations: complement for auxiliary(comp:aux)

    8. AUX tokens agree when the dependent token belongs to [NOUN] for the dependency relations: predicative complements(comp:pred)

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

    10. NOUN tokens agree when the dependent token belongs to [VERB] for the dependency relations: modifer(mod@relcl)

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

    12. NOUN tokens agree when head token belongs to [AUX, VERB] for the dependency relations: subject(subj@pass)

    13. ADJ tokens agree when the dependent token belongs to [ADJ] for the dependency relations: compound(compound@redup)

    Gender

    Examples for each leaf node:

     Leaf-0       Leaf-1       Leaf-2      

    Click on to expand the tree.