TypeError: __init__() missing 1 required positional argument: 'text' while loading the model

[Siddhijain16]

Hi @jantrienes ,
I am following the step mention at README.md but I am not able to get any result.
While loading the model I am facing this error. Please help me out how to solve it.

Select downloaded model

model = './model_bilstmcrf_ons_large-v0.2.0/final-model.pt'

Instantiate tokenizer

tokenizer = TokenizerFactory().tokenizer(corpus='ons', disable=("tagger", "ner"))

Output ==> 2022-04-11 10:22:37.046 | INFO | deidentify.tokenizer.base:tokenizer:36 - Tokenizer for corpus: ons

Load tagger with a downloaded model file and tokenizer

tagger = FlairTagger(model=model, tokenizer=tokenizer, verbose=False)

Annotate your documents

annotated_docs = tagger.annotate(documents)

Output ==>
2022-04-11 10:30:37.252 | INFO | deidentify.taggers.flair_tagger:init:20 - Load flair model from /content/drive/MyDrive/47billion/model_bilstmcrf_ons_large-v0.2.0/final-model.pt

2022-04-11 10:30:37,257 loading file /content/drive/MyDrive/47billion/model_bilstmcrf_ons_large-v0.2.0/final-model.pt
2022-04-11 10:30:59,342 SequenceTagger predicts: Dictionary with 33 tags: , O, B-Date, B-Name, I-Name, B-Hospital, B-Internal_Location, B-Care_Institute, B-Initials, B-Organization_Company, I-Organization_Company, I-Date, B-ID, I-ID, I-Care_Institute, B-Address, I-Address, B-Age, I-Age, I-Hospital, I-Internal_Location, B-Phone_fax, B-Profession, I-Profession, I-Initials, B-Other, I-Other, B-URL_IP, I-Phone_fax, B-Email, B-SSN, ,

2022-04-11 10:31:00.242 | INFO | deidentify.taggers.flair_tagger:init:22 - Finish loading flair model.

---

TypeError Traceback (most recent call last)

in ()
2 tagger = FlairTagger(model=model, tokenizer=tokenizer, verbose=False)
3 # Annotate your documents
----> 4 annotated_docs = tagger.annotate(documents)

1 frames

/usr/local/lib/python3.7/dist-packages/deidentify/methods/bilstmcrf/flair_utils.py in standoff_to_flair_sents(docs, tokenizer, verbose)
59 flair_sents = []
60 for sent in sents:
---> 61 flair_sent = Sentence()
62 for token in sent:
63 if token.text.isspace():

TypeError: init() missing 1 required positional argument: 'text'

[jantrienes]

Hi @Siddhijain16, it appears that the flair sentence API changed with the recent release v0.11. Could you please try to downgrade the flair version for now?

pip install -U flair<0.11

You can also use the dependencies listed here: https://github.com/nedap/deidentify/blob/master/environment.yml

[Siddhijain16]

Hi @Siddhijain16, it appears that the flair sentence API changed with the recent release v0.11. Could you please try to downgrade the flair version for now?

pip install -U flair<0.11

You can also use the dependencies listed here: https://github.com/nedap/deidentify/blob/master/environment.yml

Thank you @jantrienes for your quick reply. It's working now.
I have one more doubt regarding English text. By passing english text I am not able to get good annotated result. Any suggestion how can I get good result on English text?

[jantrienes]

@Siddhijain16 at this time, the pre-trained models are only available for Dutch. However, It's not too complicated to train an English deidentify model yourself. You can take a look here for pointers on how to get the English data (i2b2 and nursing notes), and how to train the models.

[Siddhijain16]

@Siddhijain16 at this time, the pre-trained models are only available for Dutch. However, It's not too complicated to train an English deidentify model yourself. You can take a look here for pointers on how to get the English data (i2b2 and nursing notes), and how to train the models.
Thank you @jantrienes for your help. I will try that !!

[jantrienes]

@Siddhijain16 the original issue should be fixed with deidentify==0.7.3. I will close this for now.