Backward rnnlm #2436
Backward rnnlm #2436
Conversation
| @@ -0,0 +1,137 @@ | |||
| #!/bin/bash | |||
There was a problem hiding this comment.
thanks! please make it a soft link to tuning/ in case we later want to update it.
| # Lattice rescoring | ||
| rnnlm/lmrescore_back.sh \ | ||
| --cmd "$decode_cmd --mem 4G" \ | ||
| --weight 0.5 --max-ngram-order $ngram_order \ |
There was a problem hiding this comment.
If you are using a weight of 0.5 for both the forward and backward passes, I'd be surprised if this weight was optimal. Because effectively the weight on the n-gram LM would be zero.
There was a problem hiding this comment.
I tuned this a bit and it seems 0.5 is the best weight.
I found another small in issue in the code which I should fix before merging this PR. Do you think we should just leave 0.5 as it is now?
There was a problem hiding this comment.
Did you try using 0.4 for both forward and backward? It's very surprising if it doesn't want any weight at all on the n-gram LM-- that always helps, as they are so complementary.
There was a problem hiding this comment.
Yes. 0.4/0.4/0.2 is also worse than 0.5/0.5/0
lattice rescoring with backward RNNLMs