Toggle navigation sidebar
HanLP Documentation
Introduction
Tutorial
Install
Configuration
Data Format
Annotations
Tokenization
The Segmentation Guidelines for the Penn Chinese Treebank (3.0)
MSR中文文本标注规范 (5.0 版)
Part-of-Speech Tagging
ctb
pku
863
NPCMJ
Universal Dependencies
Named Entity Recognition
pku
msra
ontonotes
Dependency Parsing
Stanford Dependencies Chinese
PKU Multi-view Chinese Treebank
Stanford Dependencies English
Universal Dependencies
Semantic Dependency Parsing
SemEval2016
The reduction of Minimal Recursion Semantics
Predicate-Argument Structures
Prague Czech-English Dependency Treebank
Semantic Role Labeling
Chinese Proposition Bank
English PropBank
Constituency Parsing
Chinese Tree Bank
Penn Treebank
NPCMJ
Contributing Guide
Live Demo
Python API
hanlp
hanlp
common
structure
vocab
transform
dataset
component
torch_component
components
mtl
MultiTaskLearning
tasks
classifiers
eos
tokenizers
transformer
multi_criteria
lemmatizer
taggers
transformer_tagger
rnn_tagger
ner
transformer_ner
rnn_ner
biaffine_ner
parsers
biaffine_dep
biaffine_sdp
ud_parser
crf_constituency_parser
srl
span_rank
span_bio
pipeline
sts
pretrained
mtl
eos
tok
pos
ner
dep
constituency
srl
sdp
amr
amr2text
sts
word2vec
glove
fasttext
mlm
datasets
eos
eos
resources
tok
txt
mcws_dataset
resources
pos
resources
ner
tsv
json
resources
dep
conll
resources
srl
conll2012_dataset
resources
con
constituency_dataset
resources
utils
io_util
layers
embeddings
embedding
word2vec
fasttext
char_cnn
char_rnn
transformer
transformers
encoder
tokenizer
decoders
linear_crf
biaffine_ner
hanlp_common
document
conll
configurable
constant
hanlp_restful
hanlp_trie
trie
dictionary
Java API
1.x API
Java RESTful API
Golang API
Golang RESTful API
References
References
Toggle navigation
.md
.pdf
repository
open issue
suggest edit
tokenizers
tokenizers
¶
Tokenizers.
transformer
multi_criteria
previous
eos
next
transformer
