Closed sadiayousafzai036 closed 4 years ago
Hi, could you elaborate what is length-controlled summarization in your context?
For example, if you specify length like 20 words, the pegasus model should output an abstractive summary of 20 words only of the input text.
You can specify the maximum length of output summaries by max_output_len
(the summaries can be incomplete if this is too small) or encourage longer/shorter summaries by beam_alpha
in public_params.py. But I doubt if you can control the output length as precisely as you would like, for example, a complete summary with 20 words in particular.
Got it. My question was how the model could be modified? what if i plan to migrate the model from a specific layer using transfer based learning and implement length constraint output summarized text using seq2seq approach?
Also, do you have an image or picture of detailed architecture of pegasus model? That would be really helpful.
Hi, max_output_len
and beam_alpha
can be modified in the file just mentioned above. The code of the model is available https://github.com/google-research/pegasus/tree/master/pegasus/models.
The diagram of the architecture is available in our paper. Please refer to the paper link in README.
Hi @JingqingZ , may I check with you if the gold summary is also truncated to max_output_len for computing ROUGE?
Hi @JingqingZ , may I check with you if the gold summary is also truncated to max_output_len for computing ROUGE?
yes
Thankyou @JingqingZ for your response. How the beam_alpha parameter affects length of summarized text? increasing the value of beam_alpha will result in larger summaries?
Thankyou @JingqingZ for your response. How the beam_alpha parameter affects length of summarized text? increasing the value of beam_alpha will result in larger summaries?
@sadiayousafzai036 As far as I remember, yes, larger beam_alpha
longer output, but beam_alpha
should be between 0 and 1 and typically it is around 0.6-0.9. See section 7 and equation 14 in https://arxiv.org/pdf/1609.08144.pdf
Hi,
What changes can be made to implement length based summarization?