Hi Everyone! Our new paper about the embedding policy (aka REDP) is now available: [1811.11707] Few-Shot Generalization Across Dialogue Tasks - we’ll present it at the NeurIPS conversational AI workshop next week. There’s a blog post here that explains what the paper is about, and why it matters to Rasa developers. Let me know what you think! Have you been using the Embedding Policy? We’d love to hear about your results, so let’s start a thread here. :v:

For the new Embedding you need to train stories with those chitchats and corrections. So, where is now the advantage/improvement compared to normal LSTM? Is it that you need way less stories to write such unccooperative stories, because attention layer learns not to pay attention to this part and will generalise to stories not trained?

Hi! Great feature :slight_smile: … Did you benchmark the training time ? I’m currently training a model by using this policy on a GTX 1080ti (12go) + 32Go ram + 32 core CPU and each epoch takes about ~10 min … I’m using : policies: - name: EmbeddingPolicy epochs: 2000 attn_shift_range: 5 EDIT: I’ll answer my own question : the EmbeddingPolicy should be use with --augmentation 0

yes that’s a good description :slight_smile: the point of the policy is that it can learn to re-use those patterns from just a few examples

yes! the attention mechanisms definitely require more computer power to train. You can also switch off one (or both) of the attentions to swap a bit of generalization power for compute time

@amn41 its computation is much greater then normal LSTM, and we have to write the same incoperative stories. I do not get it less number of stories. What its advantages to use it ? It has same result in my case. LSTM 300 epochs Embedding 2000 epochs.

Is this supposed to take 30 minutes to train on 2000 epochs??

@adrianhumphrey111 has already given the answer. the EmbeddingPolicy should be use with --augmentation 0 –augmentation 0 add this in your command while training

can you please give me an example for both command line and the python file way of doing that?

python -m rasa_core.train -s data/stories.md -d domain.yml -o models/dialogue -c policy.yml --augmentation 0

Embedding Policy Results

Rasa Open Source

ncoco (Nico) December 6, 2018, 1:10pm 2

This policy looks very promising

I tried to train my model, but it needs some serious processing power to even finish one epoch. Is this expected?

I am using the same hyperparams as in you paper.

Topic		Replies	Views
Embedding policy training time Rasa Open Source	17	3126	August 28, 2019
Embedding policy & story processing time explosion Rasa Open Source	3	511	December 12, 2018
How to change the rasa policy from default to EmbeddingPolicy Rasa Open Source	10	2133	June 14, 2019
Training in Rasa-X fails with EmbeddingPolicy configuration [Deprecated] Rasa X Community Edition	1	552	February 4, 2020
Embedded Policy full example of the paper Rasa Open Source	3	599	August 19, 2019

Embedding Policy Results

Related topics