initial commit

README.md

@@ -3,17 +3,17 @@ tags:
 - flair
 - token-classification
 - sequence-tagger-model
-language: de
+language: nl
 datasets:
 - conll2003
 inference: false
 ---
 
-## German NER in Flair (large model)
+## Dutch NER in Flair (large model)
 
-This is the large 4-class NER model for German that ships with [Flair](https://github.com/flairNLP/flair/).
+This is the large 4-class NER model for Dutch that ships with [Flair](https://github.com/flairNLP/flair/).
 
-F1-Score: **92,31** (CoNLL-03 German revised)
+F1-Score: **95,25** (CoNLL-03 Dutch)
 
 **! This model only works with Flair version 0.8 (will be released in the next few days) !**
 
@@ -39,10 +39,10 @@ from flair.data import Sentence
 from flair.models import SequenceTagger
 
 # load tagger
-tagger = SequenceTagger.load("flair/ner-german-large")
+tagger = SequenceTagger.load("flair/ner-dutch-large")
 
 # make example sentence
-sentence = Sentence("George Washington ging nach Washington")
+sentence = Sentence("George Washington ging naar Washington")
 
 # predict NER tags
 tagger.predict(sentence)
@@ -64,7 +64,7 @@ Span [1,2]: "George Washington"   [− Labels: PER (1.0)]
 Span [5]: "Washington"   [− Labels: LOC (1.0)]
 ```
 
-So, the entities "*George Washington*" (labeled as a **person**) and "*Washington*" (labeled as a **location**) are found in the sentence "*George Washington ging nach Washington*". 
+So, the entities "*George Washington*" (labeled as a **person**) and "*Washington*" (labeled as a **location**) are found in the sentence "*George Washington ging naar Washington*". 
 
 
 ---
@@ -77,9 +77,9 @@ The following Flair script was used to train this model:
 import torch
 
 # 1. get the corpus
-from flair.datasets import CONLL_03_GERMAN
+from flair.datasets import CONLL_03_DUTCH
 
-corpus = CONLL_03_GERMAN()
+corpus = CONLL_03_DUTCH()
 
 # 2. what tag do we want to predict?
 tag_type = 'ner'
@@ -119,7 +119,7 @@ trainer = ModelTrainer(tagger, corpus, optimizer=torch.optim.AdamW)
 # 7. run training with XLM parameters (20 epochs, small LR)
 from torch.optim.lr_scheduler import OneCycleLR
 
-trainer.train('resources/taggers/ner-german-large',
+trainer.train('resources/taggers/ner-dutch-large',
               learning_rate=5.0e-6,
               mini_batch_size=4,
               mini_batch_chunk_size=1,