Ankush Chander
Ankush Chander
Hi @Vignesh9395 , Can you try your use case with biased textrank. I think with an appropriate choice of `focus` and `bias` you should be able to bring such sentences...
Hi @Ayenem , Thanks for checking out `pytextrank`. Here"s how you can use biasedtextrank: ```python import spacy nlp = spacy.load("en_core_web_sm") nlp.add_pipe("biasedtextrank") text = "your text here" focus = "your focus...
Biased text rank is special case of personalized textrank where we add more weight to the focus nodes. In base textrank each node has weight one and then those weight...
Hey @dblaszcz, Thank you for sharing the detailed description of the issue. As you rightly figured out, applying any one for the variants "textrank", "positionrank", "biasedtextrank" attaches the extension `textrank`...
Hi @frascuchon I intend to get some clarity on this issue if it"s not already undertaken. Thanks.
Change list: - [x] handle connectionError expicitly. - [x] check for existing attribute before Api delete call Error trace now looks like ``` Traceback (most recent call last): File "/home/ankushchander/workplace/open_source/rubrix-tryout/test_ruibrix.py",...
Hi @frascuchon A generic solution for all methods sounds great. On it.
Hi @frascuchon I added the reusable decorator in the same class. Please review.
Hi @dcfidalgo That's right. But it will be useful for other tasks dataset also.
Hey @ceteri, I need some pointers to understand this requirement better. Thanks in advance.