-
Hey.
I have a question related to this Issue (https://github.com/facebookresearch/ParlAI/issues/1215).
Generally, when I shut down my server, I wait for one or two iterations of "Expiration of…
-
**Bug description**
Currently React Hooks don't work in custom frontends for tasks. Attempting to use them results in an "Invalid Hook Call" exception, due to point `#3` from this docs page:
> 3. …
-
when im hitting ctrl c parlai doesnt stop. it instead writes "Expiring all unassigned HITs" (in a loop?).
now i can just hit ctrl c again, but if i dont wait long enough the heroku server and the m…
-
Including a dependency on ask-sdk-dynamodb-persistence-adapter:2.10.0 triggers the inclusion of aws-sdk and all of its dependencies. This is despite the serverless.yml configur…
-
Hey. I am exploring ParlAI for my dialog data collection between two MTurkers. I was able to host the sample qa_data_collection task in a sandbox environment. I am wondering about the following questi…
-
**Bug description**
I failed to reproduce the human evaluation of the controllable dialogue with pre-trained model. The dialogue log in `evaluation_logs/` folder.
**Reproduction steps**
For the …
-
**Describe the bug**
I'm not sure of this is a bug or a "feature" but I would think if I uncheck HIT Tracker under Enable Scripts it should not only hide the options but also remove it from mturk as …
-
https://github.com/pannous/tensorflow-ocr
[Developing a Standard OCR Pipeline The utilization of Pc Imaginative and prescient and Deep Discovering out](http://a1a.in/developing-a-standard-ocr-pipel…
-
Hello, I am trying to create a custom task very similar to personachat or multi agent chat with HTML where two turkers are matched and chat between each other.
Currently, I am working on onboarding…
-
For atomic evaluation, the evaluation doesn't have bleu-2 score. Will you update the script to calculate the generation by bleu-2 score?