• Back to French-Sequoia 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       ADP       DET       PUNCT       VERB       ADJ       PROPN       PRON       ADV       AUX       CCONJ       NUM       SCONJ       X       SYM       INTJ       PART      

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

    2. ADJ tokens agree with their head for the dependency relations: direct object complements(comp:obj), predicative complements(comp:pred), modifer(mod)

    3. NOUN tokens agree with their head for the dependency relations: subject(subj@caus), conjunct(conj), direct object complements(comp:obj@agent), dislocated elements(dislocated), orphan(orphan), appositional modifier(appos), subject(subj), subject(subj@pass), unk(unk), vocative(vocative)

    4. VERB tokens agree with their head for the dependency relations: modifer(mod@relcl), parataxis(parataxis), complement for auxiliary(comp:aux@pass), cleft clauses(comp:cleft), complement for auxiliary(comp:aux@tense)

    5. PRON tokens agree with their head for the dependency relations: complement(comp@fixed), oblique complements(comp:obl@agent), oblique complements(comp:obl), subject(subj@expl)

    6. PROPN tokens agree with their head for the dependency relations: flat multiword expression(flat@name)

    Number

    Examples for each leaf node:

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

    Click on to expand the tree.