I am working on an application to paraphrase generation from the source sentence keywords for my PhD, but in my experience the paraphrases generated tend to be 100 to 160 words which is 3-4 times longer than my sources, even after fine-tuning.
In your opinion, what would be the best way to generate shorter paraphrases? The [No insertion] probability knob (with the risk of falling out of the pre-training domain), retraining from scratch on shorter sentences, or any other idea?
Hi,
first, thanks for your amazing work on POINTER!
I am working on an application to paraphrase generation from the source sentence keywords for my PhD, but in my experience the paraphrases generated tend to be 100 to 160 words which is 3-4 times longer than my sources, even after fine-tuning.
In your opinion, what would be the best way to generate shorter paraphrases? The [No insertion] probability knob (with the risk of falling out of the pre-training domain), retraining from scratch on shorter sentences, or any other idea?
Thanks!