Safe Haskell	None
Language	Haskell2010

NLP.Types.IOB

Synopsis

Documentation

data IOBChunk chunk tag Source #

Data type to indicate IOB tags for chunking

Constructors

BChunk (POS tag) chunk	Beging marker.
IChunk (POS tag) chunk	In chunk tag
OChunk (POS tag)	Not in a chunk.

Instances

(Eq chunk, Eq tag) => Eq (IOBChunk chunk tag) Source #
Methods (==) :: IOBChunk chunk tag -> IOBChunk chunk tag -> Bool # (/=) :: IOBChunk chunk tag -> IOBChunk chunk tag -> Bool #
(Read chunk, Read tag) => Read (IOBChunk chunk tag) Source #
Methods readsPrec :: Int -> ReadS (IOBChunk chunk tag) # readList :: ReadS [IOBChunk chunk tag] # readPrec :: ReadPrec (IOBChunk chunk tag) # readListPrec :: ReadPrec [IOBChunk chunk tag] #
(Show chunk, Show tag) => Show (IOBChunk chunk tag) Source #
Methods showsPrec :: Int -> IOBChunk chunk tag -> ShowS # show :: IOBChunk chunk tag -> String # showList :: [IOBChunk chunk tag] -> ShowS #
(ChunkTag c, Arbitrary c, Arbitrary t, Tag t) => Arbitrary (IOBChunk c t) Source #
Methods arbitrary :: Gen (IOBChunk c t) # shrink :: IOBChunk c t -> [IOBChunk c t] #

getPOS :: (ChunkTag c, Tag t) => IOBChunk c t -> POS t Source #

toTaggedSentence :: (ChunkTag c, Tag t) => [IOBChunk c t] -> TaggedSentence t Source #

parseIOBLine :: (ChunkTag chunk, Tag tag) => Text -> Either Error (IOBChunk chunk tag) Source #

Parse an IOB-chunk encoded line of text.

Assumes that the line has three space-delimeted entries, in the format: > token POSTag IOBChunk For example: > > parseIOBLine "We PRP B-NP" :: IOBChunk B.Chunk B.Tag > BChunk (POS B.PRP (Token We)) B.C_NP

iobBuilder :: (ChunkTag c, Tag t) => Text -> POS t -> Either Error (IOBChunk c t) Source #

toChunkTree :: (ChunkTag c, Tag t) => [IOBChunk c t] -> ChunkedSentence c t Source #

Turn an IOB result into a tree.

parseIOB :: (ChunkTag chunk, Tag tag) => Text -> Either Error [[IOBChunk chunk tag]] Source #

Parse an IOB-encoded corpus.

parseSentence :: (ChunkTag chunk, Tag tag) => [Text] -> Either Error [IOBChunk chunk tag] Source #

getSentences :: Text -> [[Text]] Source #

Just split a body of text into lines, and then into "paragraphs". Each resulting sub list is separated by empty lines in the original text.

e.g.; > > getSentences "Henjumpedn.nnShenjumpedn." > [[He, "jumped", "."], [She,"jumped", "."]]