sentence scores for summarization

[shyamcody]

trafficstars

In the text rank extension, we have a summarization method; but that option will be more effective if you expose the sentence score as a touple with the sentences that come out as summarization output. It can be asked by an input parameter whether the user just wants a summary or also the sentence scores. Let me know if there is a way to get the sentence scores in current settings too. If it is not possible, then I would like to try and add a PR for the same if allowed. Thanks.

[ceteri]

Thank you @shyamcody - we just did a relatively large refactoring of the code base, heading toward the spaCy 3.x release, and now this should be much simpler. I may be able to get it into the next release.

[ceteri]

Hi @shyamcody,

In the current main branch, there are two new methods for the TextRank object:

• add get_unit_vector() method to expose the characteristic unit vector
• add calc_sent_dist() method to expose the sentence distance measures (for summarization)

Will these provide what you were asking about?

These haven't been pushed to a new PyPi release just yet. Would be great to get your feedback first.

[shyamcody]

Hey @ceteri thanks for the mention; I will check and give you my feedback