gonlp

Documentation

Index

• Variables
• func MaxScore(m map[string]float64) string
• func ParseOntonotes(ontoPath string, outPath string) error
• func Round(val float64, roundOn float64, places int) (newVal float64)
• type AveragedPerceptron
  • func NewAveragedPerceptron() *AveragedPerceptron
  • func (ap *AveragedPerceptron) AverageWeights()
  • func (ap *AveragedPerceptron) Predict(features map[string]int) string
  • func (ap *AveragedPerceptron) Update(truth string, guess string, features map[string]int)
• type BaseTagger
• type FeatureClass
• type Leaves
• type Pair
• type PairList
  • func SortMapKV(m map[string]float64) PairList
  • func (p PairList) Len() int
  • func (p PairList) Less(i, j int) bool
  • func (p PairList) Swap(i, j int)
• type PerceptronTagger
  • func NewPerceptronTagger(tokenizer Tokenizer, load bool, path string) (*PerceptronTagger, error)
  • func (t *PerceptronTagger) Tag(sentence string) ([]Tag, error)
  • func (t *PerceptronTagger) Train(sentences []WordsTags, savePath string, iter int)
• type PosTagger
• type RegexpTokenizer
  • func NewRegexpTokenizer(pattern string) *RegexpTokenizer
  • func (t *RegexpTokenizer) Tokenize(s string) []Token
• type SplitTokenizer
  • func NewSplitTokenizer(sep string) *SplitTokenizer
  • func (t *SplitTokenizer) Tokenize(s string) []Token
• type SyntaxParser
  • func NewSyntaxParser() *SyntaxParser
  • func (sp *SyntaxParser) Parse(taggedTokens []TaggedToken) (Tree, error)
  • func (sp *SyntaxParser) PrettyPrint(tree Tree, level int)
• type Tag
• type TaggedToken
• type Token
  • func Tokenize(text string, tokenizer Tokenizer) []Token
• type Tokenizer
• type Tree
• type TreeBankTokenizer
  • func NewTreeBankTokenizer() *TreeBankTokenizer
  • func (t *TreeBankTokenizer) Tokenize(s string) []Token
• type WordsTags

Variables

var (
	ErrBadThing        = errors.New("error description")
	ErrAnotherBadThing = errors.New("error description")
)

var (
	START          = []string{"-START-", "-START2-"}
	END            = []string{"-END-", "-END2-"}
	MODEL_GOB_PATH = "avp_model.gob"
)

Functions

func MaxScore

func MaxScore(m map[string]float64) string

func ParseOntonotes

func ParseOntonotes(ontoPath string, outPath string) error

func Round

func Round(val float64, roundOn float64, places int) (newVal float64)

https://gist.github.com/pelegm/c48cff315cd223f7cf7b

Types

type AveragedPerceptron

type AveragedPerceptron struct {
	Classes map[string]struct{}
	// contains filtered or unexported fields
}

func NewAveragedPerceptron

func NewAveragedPerceptron() *AveragedPerceptron

func (*AveragedPerceptron) AverageWeights

func (ap *AveragedPerceptron) AverageWeights()

func (*AveragedPerceptron) Predict

func (ap *AveragedPerceptron) Predict(features map[string]int) string

func (*AveragedPerceptron) Update

func (ap *AveragedPerceptron) Update(truth string, guess string, features map[string]int)

type BaseTagger

type BaseTagger struct {
	// contains filtered or unexported fields
}

type FeatureClass

type FeatureClass struct {
	// contains filtered or unexported fields
}

type Leaves

type Leaves interface {
}

type Pair

type Pair struct {
	Key   string
	Value float64
}

type PairList

type PairList []Pair

func SortMapKV

func SortMapKV(m map[string]float64) PairList

func (PairList) Len

func (p PairList) Len() int

func (PairList) Less

func (p PairList) Less(i, j int) bool

func (PairList) Swap

func (p PairList) Swap(i, j int)

type PerceptronTagger

type PerceptronTagger struct {
	Model  *AveragedPerceptron
	TagMap map[string]string

	BaseTagger
	// contains filtered or unexported fields
}

func NewPerceptronTagger

func NewPerceptronTagger(tokenizer Tokenizer, load bool, path string) (*PerceptronTagger, error)

func (*PerceptronTagger) Tag

func (t *PerceptronTagger) Tag(sentence string) ([]Tag, error)

func (*PerceptronTagger) Train

func (t *PerceptronTagger) Train(sentences []WordsTags, savePath string, iter int)

type PosTagger

type PosTagger interface {
	Tag(string) []Tag
}

type RegexpTokenizer

type RegexpTokenizer struct {
	// contains filtered or unexported fields
}

func NewRegexpTokenizer

func NewRegexpTokenizer(pattern string) *RegexpTokenizer

func (*RegexpTokenizer) Tokenize

func (t *RegexpTokenizer) Tokenize(s string) []Token

type SplitTokenizer

type SplitTokenizer struct {
	// contains filtered or unexported fields
}

func NewSplitTokenizer

func NewSplitTokenizer(sep string) *SplitTokenizer

func (*SplitTokenizer) Tokenize

func (t *SplitTokenizer) Tokenize(s string) []Token

type SyntaxParser

type SyntaxParser struct {
}

func NewSyntaxParser

func NewSyntaxParser() *SyntaxParser

func (*SyntaxParser) Parse

func (sp *SyntaxParser) Parse(taggedTokens []TaggedToken) (Tree, error)

func (*SyntaxParser) PrettyPrint

func (sp *SyntaxParser) PrettyPrint(tree Tree, level int)

type Tag

type Tag struct {
	Token Token
	Pos   string
}

type TaggedToken

type TaggedToken struct {
	Token string
	Tag   string
}

type Token

type Token struct {
	Word  string
	Start int
	End   int
}

func Tokenize

func Tokenize(text string, tokenizer Tokenizer) []Token

type Tokenizer

type Tokenizer interface {
	Tokenize(string) []Token
}

type Tree

type Tree struct {
	Type   string
	Leaves []Leaves
}

type TreeBankTokenizer

type TreeBankTokenizer struct {
	// contains filtered or unexported fields
}

func NewTreeBankTokenizer

func NewTreeBankTokenizer() *TreeBankTokenizer

func (*TreeBankTokenizer) Tokenize

func (t *TreeBankTokenizer) Tokenize(s string) []Token

type WordsTags

type WordsTags struct {
	Words []string
	Tags  []string
}