sumy
sumy copied to clipboard
miso-belica
Module for automatic summarization of text documents and HTML pages.
I'm not sure if it's okay to mention this here but I made a HuggingFace space for sumy that I think makes it easy and quick to try out the...
how could I extract a specific number of keywords instead of sentence with python API?
Not really an issue, just a question. So I'm summarising books by paragraphs, and I was thinking to get the main plot 'happening' it would be beneficial to prioratise sentences...
sumbasic failed on text: [common.txt](https://github.com/miso-belica/sumy/files/9075022/common.txt) ``` Traceback (most recent call last): File "summerisers.py", line 39, in summary = " ".join([obj._text for obj in s(parser.document, sentenceCntOut)]) File "C:\py38_64\lib\site-packages\sumy\summarizers\sum_basic.py", line 27, in...
I use [NLTK](http://nltk.org/) to tokenize text into sentences & words. But that's big package. Maybe something smaller would be better. Something like https://bitbucket.org/trebor74hr/text-sentence/overview
it seems to work fine with small text data however when i tried to use the same for document(approx 2000 lines) , it became way too slow.. and took around...
I'm working on replacing sumy in an existing project with a BERT based summarization model. Would you be interested in me making a PR which adds a BERTSummarizer class to...
In command `sumy_eval random modsum/some_name.2.txt --language=english --file=docs/text.txt --format=plaintext` How I can change different parameters of Rouge evaluation like `-a -c 95 -b 665 -m -n 4 -w 1.2`?
Good morning first of all I wanted to congratulate with you for this awesome repository, it really is very well made and the practical results are great, on top of...
Metadata
Owner
Metadata
Module for automatic summarization of text documents and HTML pages.