DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue

Stream data with DDA:

from dagshub.streaming import DagsHubFilesystem

fs = DagsHubFilesystem(".", repo_url="https://dagshub.com/DagsHub-Datasets/dialoglue-dataset")

fs.listdir("s3://dialoglue")

Description:

This bucket contains the checkpoints used to reproduce the baseline results reported in the DialoGLUE benchmark hosted on EvalAI (https://evalai.cloudcv.org/web/challenges/challenge-page/708/overview). The associated scripts for using the checkpoints are located here: https://github.com/alexa/dialoglue. The associated paper describing the benchmark and checkpoints is here: https://arxiv.org/abs/2009.13570. The provided checkpoints include the CONVBERT model, a BERT-esque model trained on a large open-domain conversational dataset. It also includes the CONVBERT-DG and BERT-DG checkpoints described in the linked paper.

Contact:

This bucket contains the checkpoints used to reproduce the baseline results reported in the DialoGLUE benchmark hosted on EvalAI (https://evalai.cloudcv.org/web/challenges/challenge-page/708/overview). The associated scripts for using the checkpoints are located here: https://github.com/alexa/dialoglue. The associated paper describing the benchmark and checkpoints is here: https://arxiv.org/abs/2009.13570. The provided checkpoints include the CONVBERT model, a BERT-esque model trained on a large open-domain conversational dataset. It also includes the CONVBERT-DG and BERT-DG checkpoints described in the linked paper.

Update Frequency:

Not currently being updated

Managed By:

https://www.amazon.com/

Resources:

1. resource:
   • Description: DialoGLUE checkpoints
   • ARN: arn:aws:s3:::dialoglue
   • Region: us-east-1
   • Type: S3 Bucket
   • Explore: Browse Bucket

Tags:

amazon.science, natural language processing, machine learning, conversation data

Publication:

1. publication:
   • Title: DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue
   • URL: https://arxiv.org/abs/2009.13570
   • AuthorName: Shikib Mehri, Mihail Eric, Dilek Hakkani-Tur