Safe Haskell	None

NLP.Types.Tree

Synopsis

Documentation

data Sentence Source

A sentence of tokens without tags. Generated by the tokenizer. (tokenizer :: Text -> Sentence)

Constructors

Sent [Token]

Instances

Eq Sentence
Read Sentence
Show Sentence
Arbitrary Sentence

tokens :: Sentence -> [Token]Source

Extract the token list from a Sentence

applyTags :: Tag t => Sentence -> [t] -> TaggedSentence tSource

Apply a parallel list of Tags to a Sentence.

data ChunkedSentence chunk tag Source

A chunked sentence has POS tags and chunk tags. Generated by a chunker.

(chunker :: (Chunk chunk, Tag tag) => TaggedSentence tag -> ChunkedSentence chunk tag)

Constructors

ChunkedSent [ChunkOr chunk tag]

Instances

(Eq chunk, Eq tag) => Eq (ChunkedSentence chunk tag)
(Read chunk, Read tag) => Read (ChunkedSentence chunk tag)
(Show chunk, Show tag) => Show (ChunkedSentence chunk tag)
(ChunkTag c, Arbitrary c, Arbitrary t, Tag t) => Arbitrary (ChunkedSentence c t)
(Monad m, ChunkTag c, Tag t) => Stream (ChunkedSentence c t) m (ChunkOr c t)

data ChunkOr chunk tag Source

A data type to represent the portions of a parse tree for Chunks. Note that this part of the parse tree could be a POS tag with no chunk.

Constructors

Chunk_CN (Chunk chunk tag)
POS_CN (POS tag)

Instances

(Eq chunk, Eq tag) => Eq (ChunkOr chunk tag)
(Read chunk, Read tag) => Read (ChunkOr chunk tag)
(Show chunk, Show tag) => Show (ChunkOr chunk tag)
(ChunkTag c, Arbitrary c, Arbitrary t, Tag t) => Arbitrary (ChunkOr c t)
(Monad m, ChunkTag c, Tag t) => Stream (ChunkedSentence c t) m (ChunkOr c t)

data Chunk chunk tag Source

A Chunk that strictly contains chunks or POS tags.

Constructors

Chunk chunk [ChunkOr chunk tag]

Instances

(Eq chunk, Eq tag) => Eq (Chunk chunk tag)
(Read chunk, Read tag) => Read (Chunk chunk tag)
(Show chunk, Show tag) => Show (Chunk chunk tag)
(ChunkTag c, Arbitrary c, Arbitrary t, Tag t) => Arbitrary (Chunk c t)

showChunkedSent :: (ChunkTag c, Tag t) => ChunkedSentence c t -> TextSource

data TaggedSentence tag Source

A tagged sentence has POS Tags. Generated by a part-of-speech tagger. (tagger :: Tag tag => Sentence -> TaggedSentence tag)

Constructors

TaggedSent [POS tag]

Instances

Eq tag => Eq (TaggedSentence tag)
Read tag => Read (TaggedSentence tag)
Show tag => Show (TaggedSentence tag)
(Arbitrary t, Tag t) => Arbitrary (TaggedSentence t)
(Monad m, Tag t) => Stream (TaggedSentence t) m (POS t)

printTS :: Tag t => TaggedSentence t -> TextSource

Generate a Text representation of a TaggedSentence in the common tagged format, eg:

 "the/at dog/nn jumped/vbd ./."

stripTags :: Tag t => TaggedSentence t -> Sentence Source

Remove the tags from a tagged sentence

unzipTags :: Tag t => TaggedSentence t -> (Sentence, [t])Source

Extract the tags from a tagged sentence, returning a parallel list of tags along with the underlying Sentence.

unzipChunks :: (ChunkTag c, Tag t) => ChunkedSentence c t -> (TaggedSentence t, [c])Source

combine :: Tag t => [TaggedSentence t] -> [TaggedSentence t] -> [TaggedSentence t]Source

Combine the results of POS taggers, using the second param to fill in tagUNK entries, where possible.

combineSentences :: Tag t => TaggedSentence t -> TaggedSentence t -> TaggedSentence tSource

Merge TaggedSentence values, preffering the tags in the first TaggedSentence. Delegates to pickTag.

pickTag :: Tag t => POS t -> POS t -> POS tSource

Returns the first param, unless it is tagged tagUNK. Throws an error if the text does not match.

mkChunk :: (ChunkTag chunk, Tag tag) => chunk -> [ChunkOr chunk tag] -> ChunkOr chunk tagSource

Helper to create ChunkOr types.

mkChink :: (ChunkTag chunk, Tag tag) => tag -> Token -> ChunkOr chunk tagSource

Helper to create ChunkOr types that just hold POS tagged data.

data POS tag Source

A POS-tagged token.

Constructors

POS
Fields posTag :: tag posToken :: Token

Instances

Eq tag => Eq (POS tag)
Read tag => Read (POS tag)
Show tag => Show (POS tag)
(Arbitrary t, Tag t) => Arbitrary (POS t)
(Monad m, Tag t) => Stream (TaggedSentence t) m (POS t)

showPOStok :: Tag tag => POS tag -> TextSource

Show the underlying text token only.

showPOStag :: Tag tag => POS tag -> TextSource

printPOS :: Tag tag => POS tag -> TextSource

Show the text and tag.

data Token Source

Raw tokenized text.

Token has a IsString instance to simplify use.

Constructors

Token Text

Instances

Eq Token
Read Token
Show Token
IsString Token
Arbitrary Token

showTok :: Token -> TextSource

Extract the text of a Token

suffix :: Token -> TextSource

Extract the last three characters of a Token, if the token is long enough, otherwise returns the full token text.

unTS :: Tag t => TaggedSentence t -> [POS t]Source

Extract the list of POS tags from a TaggedSentence

tsLength :: Tag t => TaggedSentence t -> Int Source

Calculate the length of a TaggedSentence (in terms of the number of tokens).

tsConcat :: Tag t => [TaggedSentence t] -> TaggedSentence tSource

Brutally concatenate two TaggedSentences

contains :: Tag t => TaggedSentence t -> Text -> Bool Source

True if the input sentence contains the given text token. Does not do partial or approximate matching, and compares details in a fully case-sensitive manner.

containsTag :: Tag t => TaggedSentence t -> t -> Bool Source

True if the input sentence contains the given POS tag. Does not do partial matching (such as prefix matching)

posTagMatches :: Tag t => t -> POS t -> Bool Source

Compare the POS-tag token with a supplied tag string.

posTokMatches :: Tag t => Text -> POS t -> Bool Source

Compare the POS-tagged token with a text string.

tokenMatches :: Text -> Token -> Bool Source

Compare a token with a text string.