HanLP: Han Language Processing

thumb_up Good

Live Demo

Any multilingual sentence within 200 characters
SDP standard
Use multilingual model.

Linguistics

Dep  
──── 
┌──► 
│┌─► 
└┴── 
To 
── 
第四 
军医 
大学 
Relati 
────── 
nummod 
nmod   
root   
Le 
── 
第四 
军医 
大学 
PoS  
──── 
NUM  
NOUN 
NOUN 
To 
── 
第四 
军医 
大学 
NER Type    
─────────── 
───►ORDINAL 
◄─┐         
◄─┴►ORG     
To 
── 
第四 
军医 
大学 
PoS     3     4 
────────────────
NUM ───►QP──┐   
NOUN──┐     ├►NP
NOUN──┴►NP──┘   

Lexical

                            第四 军医 大学
T1 NUM 0 2 第四
#1	AnnotatorNotes	T1	numeral
T2 NOUN 3 5 军医
#2	AnnotatorNotes	T2	noun
T3 NOUN 6 8 大学
#3	AnnotatorNotes	T3	noun
T4 ORDINAL 0 2 第四
T5 ORG 3 8 军医 大学

                            
                        

Syntactics

                            1	第四	第四	NUM	NUM	_	3	nummod	_	_
2	军医	军医	NOUN	NOUN	_	3	nmod	_	_
3	大学	大学	NOUN	NOUN	_	0	root	_	_

                            
                        

Semantics

%3 1 第四 2 军医 1->2 orphan 3 大学 1->3 orphan

Introduction

The multilingual NLP library for researchers and companies, built on PyTorch and TensorFlow 2.x, for advancing state-of-the-art deep learning techniques in both academia and industry. HanLP was designed from day one to be efficient, user friendly and extendable.

Thanks to open-access corpora like Universal Dependencies and OntoNotes, HanLP 2.1 now offers 10 joint tasks on 104 languages: tokenization, lemmatization, part-of-speech tagging, token feature extraction, dependency parsing, constituency parsing, semantic role labeling, semantic dependency parsing, abstract meaning representation (AMR) parsing. See also GitHub

HanLP versions