ConvLab-3
ConvLab-3 copied to clipboard
ConvLab
Hello, I have been trying to understand the code inthe mulutwoz_eval.py file, to be able to extend it on any dataset, at the beginning I see a repeated block of...
**Describe the feature** Expansion of SLU to new languages requires much work on manual annotation of data. In order to significantly reduce amount of work, LLMs can be used to...
Hi, I am facing this following error, while optimizing the PPO policy: ValueError: expected sequence of length 361 at dim 1 (got 208) I first simulated a dialogue between the...
Hi, I am facing the following error: **_ValueError: too many values to unpack (expected 4)_**, while trying to simulate and generate dialogues between the user and the system: To replicate...
Hi, I am facing the following error, while trying to simulate and generate dialogues between the user and the system: To replicate the error, here is the code that I...
Hi there, I noticed that there are [APIs](https://github.com/ConvLab/ConvLab-3/blob/master/convlab/util/unified_datasets_util.py) to load NLU, DST, Policy and NLG data in unified data format. Besides, I found the training and evaluation guide for NLU/DST/NLG...
**Describe the feature** Thank you for your work and for adding LLM-based models to the platform. I would be very grateful to see a working example of LLM-based user simulator...
I have a question regarding the training loss for T5 NLG. If we do not set 'metric_for_best_model' to 'bleu,' as shown in the picture below, is it automatically set to...
**Describe the bug** The script `example_train.py` in Train RL Policies does not run. **To Reproduce** Steps to reproduce the behavior: ``` cd tutorials/Train_RL_Policies python example_train.py ``` Error: ``` Traceback (most...
**Describe the bug** Missing module `convlab.nlg.scgpt.utils` for SC-GPT. **To Reproduce** Steps to reproduce the behavior: 1. Run the following command: `python -m convlab.laug.Text_Paraphrasing.Text_Paraphrasing` **Expected behavior** Should print the paraphrased text...