HanLP: Han Language Processing

thumb_up Good

Live Demo

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

Linguistics

Dep Tree   
────────── 
       ┌─► 
    ┌─►├── 
    │  └─► 
    │  ┌─► 
┌┬┬─┴──┴── 
│││  ┌───► 
│││  │┌──► 
│││  ││┌─► 
││└─►└┴┴── 
││    ┌──► 
││    │┌─► 
│└───►└┴── 
└────────► 
Token            
──────────────── 
In               
2021             
,                
HanLPv2.1        
delivers         
state-of-the-art 
multilingual     
NLP              
techniques       
to               
production       
environments     
.                
Relation 
──────── 
case     
obl      
punct    
nsubj    
root     
amod     
amod     
compound 
obj      
case     
compound 
obl      
punct    
Lemma            
──────────────── 
in               
2021             
,                
HANlpv2.1        
deliver          
state-of-the-art 
multilingual     
NLP              
technique        
to               
production       
environment      
.                
PoS   
───── 
ADP   
NUM   
PUNCT 
PROPN 
VERB  
ADJ   
ADJ   
PROPN 
NOUN  
ADP   
NOUN  
NOUN  
PUNCT 
Tok              
──────────────── 
In               
2021             
,                
HanLPv2.1        
delivers         
state-of-the-art 
multilingual     
NLP              
techniques       
to               
production       
environments     
.                
NER Type        
─────────────── 
                
───►DATE        
                
───►WORK_OF_ART 
                
                
                
                
                
                
                
                
                
Tok              
──────────────── 
In               
2021             
,                
HanLPv2.1        
delivers         
state-of-the-art 
multilingual     
NLP              
techniques       
to               
production       
environments     
.                
SRL PA1      
──────────── 
◄─┐          
◄─┴►ARGM-TMP 
             
───►ARG0     
╟──►PRED     
             
             
             
             
◄─┐          
  ├►ARG2     
◄─┘          
             
Tok              
──────────────── 
In               
2021             
,                
HanLPv2.1        
delivers         
state-of-the-art 
multilingual     
NLP              
techniques       
to               
production       
environments     
.                
PoS      3       4       5       6
──────────────────────────────────
ADP ───────────┐                  
NUM ────►NP ───┴────────►PP ───┐  
PUNCT──────────────────────────┤  
PROPN───────────────────►NP────┤  
VERB ──────────────────┐       │  
ADJ ───┐               │       │  
ADJ    │               │       │  
PROPN  ├────────►NP────┼►VP────┼►S
NOUN ──┘               │       │  
ADP ───────────┐       │       │  
NOUN ──┐       ├►PP ───┘       │  
NOUN ──┴►NP ───┘               │  
PUNCT──────────────────────────┘  

Lexical

Syntactics

Semantics

%3 1 In 2 2021 1->2 ARG2 3 , 1->3 orphan 4 HanLPv2.1 1->4 orphan 5 delivers 1->5 orphan 6 state-of-the-art 1->6 orphan 7 multilingual 1->7 orphan 8 NLP 1->8 orphan 10 to 1->10 orphan 11 production 1->11 orphan 13 . 1->13 orphan 5->4 ARG1 9 techniques 5->9 ARG2 12 environments 5->12 ARG3 6->9 ARG1 7->9 ARG1 8->9 compound 11->12 compound

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