[−][src]Trait punkt::params::TrainerParameters

pub trait TrainerParameters: DefinesSentenceEndings + DefinesInternalPunctuation {
    const ABBREV_LOWER_BOUND: f64;
    const ABBREV_UPPER_BOUND: f64;
    const IGNORE_ABBREV_PENALTY: bool;
    const COLLOCATION_LOWER_BOUND: f64;
    const SENTENCE_STARTER_LOWER_BOUND: f64;
    const INCLUDE_ALL_COLLOCATIONS: bool;
    const INCLUDE_ABBREV_COLLOCATIONS: bool;
    const COLLOCATION_FREQUENCY_LOWER_BOUND: f64;
}

Configurable parameters for a trainer.

Associated Constants

const ABBREV_LOWER_BOUND: f64

Lower bound score for a token to be considered an abbreviation.

const ABBREV_UPPER_BOUND: f64

Upper bound score for a token to be considered an abbreviation.

const IGNORE_ABBREV_PENALTY: bool

Disables the abbreviation penalty which exponentially penalizes occurances of words without a trailing period.

const COLLOCATION_LOWER_BOUND: f64

Lower bound score for two tokens to be considered a collocation

const SENTENCE_STARTER_LOWER_BOUND: f64

Lower bound score for a token to be considered a sentence starter.

const INCLUDE_ALL_COLLOCATIONS: bool

Include all pairs where the first token ends with a period.

const INCLUDE_ABBREV_COLLOCATIONS: bool

Include all pairs where the first is an abbreviation. Overridden by include_all_collocations.

const COLLOCATION_FREQUENCY_LOWER_BOUND: f64

Minimum number of times a bigram appears in order to be considered a collocation.

Loading content...

Implementors

Loading content...