Large comments , The aspects and sentiments are not getting extracted

[dexter16111989]

Below is my code , If the text is too long the aspect & sentiment are not getting extracted , Please correct me if I am doing something wrong.

from pyabsa import AspectTermExtraction as ATEPC, available_checkpoints

# you can view all available checkpoints by calling available_checkpoints()
checkpoint_map = available_checkpoints()

aspect_extractor = ATEPC.AspectExtractor('multilingual',
                                         auto_device=True,  # False means load model on CPU
                                         cal_perplexity=True,
                                         )

# instance inference
atepc_result=aspect_extractor.predict(["As per my previous review, I've had a few bumps along the road in the early days with Amazon. However after ordering frequently for over 2 years now, I can honestly say that either these issues have been resolved, or I'm always compensated in some way for any inconvenience." ],
                         save_result=True,
                         print_result=True,  # print the result
                         ignore_error=True,  # ignore the error when the model cannot predict the input
                         )

O/P of aptec_results

[yangheng95]

There are two possible reasons,

1. The text is too long, please try to cut the text
2. You data does not well fit the training data, you can try to train the model based on your dataset
   If these information does not help, please comment and @me. Thanks.

[SuryaprakashM]

Hi,
Is there any specific limit on the length of text ?

[yangheng95]

80 words for the provided checkpoints and 512 maximum in your own training (set config.max_seq_len=512)

[SuryaprakashM]

Thank you !

[combokang]

80 words for the provided checkpoints and 512 maximum in your own training (set config.max_seq_len=512)

Any chance to use your models with over 512 tokens?