nlpaug
nlpaug copied to clipboard
makcedward
Data augmentation for NLP
Using Context-word-enbedding augmenter: English: ```python text = 'hi how are you' context_aug = naw.ContextualWordEmbsAug( model_path='bert-base-uncased', action="substitute") augmented_text = context_aug.augment(text) print("Original:") print(text) print("Augmented Text:") print(augmented_text) ``` output is ok: ``` Original:...
When i use **word.AntonymAug**, **word.ContextualWordEmbsAug**, **word.RandomWordAug** or any other **word.augmenter** that use NLTK, some times it rises the error: - Full stack trace at https://pastebin.com/br11u7Mw) - Just the tail of...
Hello! Thanks first for your great work! I am doing text augmentation but wondering how to delete some certain words from my document corpus. I see one can delete words...
Hi, I got one question about the Synonyms and Antonyms function. Can your tool consider the tense when call the Synonyms and Antonyms functions? For example, the synonym for `agrees`...
**code** : import nlpaug.augmenter.word as naw aug = naw.ContextualWordEmbsAug(model_path='bert-base-uncased', action="insert",device ='cuda') text = 'The quick brown fox jumps over the lazy dog' augmented_text = aug.augment(text) print("Original:") print(text) print("Augmented Text:") print(augmented_text)...
This is my first time submitting an issue on Github, my apologies in advance if I did not give enough information for this to be resolved -- please let me...
**Hi NLPAug Team! I wanted to propose a integration with the Hugging Face Hub.** This integration would allow you to freely download/upload augmenter models from/to the Hugging Face Hub: https://huggingface.co/....
As the include_detail features now deprecated, whats the right way of aligning NER labels with augmented text?
Hi, may I know how to specify the percent of words in the sentence that will be changed? For example, if I want to generate several new texts based on...
When I augment with model='fasttext' aug = naw.WordEmbsAug(model_type='fasttext', model='train_ft.bin', action="substitute") augmented_text = aug.augment(text) It raises error as below: /usr/local/lib/python3.7/dist-packages/nlpaug/base_augmenter.py in augment(self, data, n, num_thread) 103 # Single Thread 104 if...
