NLP.POS.LiteralTagger

Documentation

tag :: Tag t => Map Text t -> CaseSensitive -> [Sentence] -> [TaggedSentence t]

tagSentence :: Tag t => Map Text t -> CaseSensitive -> Sentence -> TaggedSentence t

mkTagger :: Tag t => Map Text t -> CaseSensitive -> Maybe (POSTagger t) -> POSTagger t

Create a Literal Tagger using the specified back-off tagger as a fall-back, if one is specified.

This uses a tokenizer adapted from the tokenize package for a tokenizer, and Erik Kow's fullstop sentence segmenter as a sentence splitter.

taggerID :: ByteString

readTagger :: Tag t => ByteString -> Maybe (POSTagger t) -> Either String (POSTagger t)

deserialization for Literal Taggers. The serialization logic is in the posSerialize record of the POSTagger created in mkTagger.

data CaseSensitive

Boolean type to indicate case sensitivity for textual comparisons.

Constructors

Sensitive

Insensitive

Instances

Read CaseSensitive

Methods

readsPrec :: Int -> ReadS CaseSensitive

readList :: ReadS [CaseSensitive]

readPrec :: ReadPrec CaseSensitive

readListPrec :: ReadPrec [CaseSensitive]

Show CaseSensitive

Methods

showsPrec :: Int -> CaseSensitive -> ShowS

show :: CaseSensitive -> String

showList :: [CaseSensitive] -> ShowS

Generic CaseSensitive

Associated Types

type Rep CaseSensitive :: * -> *

Methods

from :: CaseSensitive -> Rep CaseSensitive x

to :: Rep CaseSensitive x -> CaseSensitive

Arbitrary CaseSensitive

Methods

arbitrary :: Gen CaseSensitive

shrink :: CaseSensitive -> [CaseSensitive]

Serialize CaseSensitive

Methods

put :: Putter CaseSensitive

get :: Get CaseSensitive

type Rep CaseSensitive

type Rep CaseSensitive = D1 (MetaData "CaseSensitive" "NLP.Types.General" "chatter-0.9.1.0-CnWxxDeMROyIxVsZb3fGkc" False) ((:+:) (C1 (MetaCons "Sensitive" PrefixI False) U1) (C1 (MetaCons "Insensitive" PrefixI False) U1))

protectTerms :: [Text] -> CaseSensitive -> Tokenizer

Create a tokenizer that protects the provided terms (to tokenize multi-word terms)