seq2seq-summarizer

seq2seq-summarizer copied to clipboard

The computaion of neg_reward is wrong

1

This code uses batch-averaged (sample_rouge - baseline rouge), but it don't make sense in math and this item should be sample-wise because what we really want to maximize is this:

zzxn

Hello, @ymfa I am now training this model. Could you tell me what is the ideal rouge score? Thank you.

Jimmy5217

./ROUGE-1.5.5.pl: Permission denied

3

I run the code in GPU server,but when run the rouge to value the result ,the error come out: /bin/sh: 1: ./ROUGE-1.5.5.pl: Permission denied  Do you know what happen?...

panpan197

word vector

1

sorry, but how can I get data/.vector_cache/glove.6B.100d.txt?

wwwjs

when i try run the script make_cnndm_data.py it tells a error

2

i am new in pythin & nlp, so i am not sure how to solve this problem. i will appreciate you if you can tell me how to solve that...

hommy112

Hello, i have a trouble. when i train the model by using the data of google. the trainn loss is decrease, but the valid loss is increase at about 6....

TianlinZhang668

I can't get the data to train. Can you give me the data or the address of your data?

3

ZephyrChenzf

i want to ask about the end_token of the generating summarization. for example. extras needed for film that starts island in the island ; ' for rise again '' film...

TianlinZhang668

The implementation of coverage mechanism seems to be wrong.

4

The author of pointer-generator propose a method called coverage mechanism. Coverage vector, which is the sum of attention distributions over all previous decoder timesteps, but the coverage vector in this...

NileZhou

How about results

5

Good job. How about rouge scores?

xyznlp