AttributeError with Tokenizer about aspect-based-sentiment-analysis HOT 3 OPEN

This fixes the first issue:

from transformers import BertTokenizer
tokenizer = BertTokenizer.from_pretrained(model_name)

from aspect-based-sentiment-analysis.

Thank you for your solution. Now I get another error:

Traceback (most recent call last):
File "/Users/petar.ulev/Documents/prepare_sentiment_data/spacystuff.py", line 29, in
task = nlp.preprocess(text=text, aspects=aspects)
File "/Users/petar.ulev/Documents/prepare_sentiment_data/venv/lib/python3.8/site-packages/aspect_based_sentiment_analysis/pipelines.py", line 213, in preprocess
spans = self.text_splitter(text) if self.text_splitter else [text]
File "/Users/petar.ulev/Documents/prepare_sentiment_data/venv/lib/python3.8/site-packages/aspect_based_sentiment_analysis/text_splitters.py", line 17, in wrapper
sentences = [sent.string.strip() for sent in doc.sents]
File "/Users/petar.ulev/Documents/prepare_sentiment_data/venv/lib/python3.8/site-packages/aspect_based_sentiment_analysis/text_splitters.py", line 17, in
sentences = [sent.string.strip() for sent in doc.sents]
AttributeError: 'spacy.tokens.span.Span' object has no attribute 'string'

Did you experience it as well?

from aspect-based-sentiment-analysis.

Can you try this?

sentences = [sent.text.strip() for sent in doc.sents]

from aspect-based-sentiment-analysis.