Question about passive voice

[airship-explorer]

In your paper "Semi-Supervised Bootstrapping of Relationship Extractors with Distributional Semantics", you said "BREDS also tries to identify the passive voice using part-of-speech (PoS) tags ,..., it will swap the order of the entities when producing a relational triple".

But I can't find this process in your code. If BREDS detect the passive voice and swap the entities, about the words before the first entity and words after the second entity? Can you give
me some advice? Thank you!

[davidsbatista]

You can see the code that detects the passive voice here:

https://github.com/davidsbatista/BREDS/blob/master/breds/reverb.py#L277

It's a bit messy and I plant to change it so it uses the NLTK's RegexpParser, instead of long list of regexes and if statements, like I did here:

http://www.davidsbatista.net/blog/2017/05/08/ReVerb/

The before and after words remain the same, it's only the relationship that changes directions, see examples in the paper.