InstructDial
Instruction tuning is an emergent paradigm in NLP wherein natural language instructions are leveraged with language models to induce zero-shot performance on unseen tasks. Instructions have been shown to enable good performance on unseen tasks and datasets in both large and small language models. Dialogue is an especially interesting area to explore instruction tuning because dialogue systems perform multiple kinds of tasks related to language (e.g., natural language understanding and generation, domain-specific interaction), yet instruction tuning has not been systematically explored for dialogue-related tasks. We introduce InstructDial, an instruction tuning framework for dialogue, which consists of a repository of 48 diverse dialogue tasks in a unified text-to-text format created from 59 openly available dialogue datasets. Next, we explore cross-task generalization ability on models tuned on InstructDial across diverse dialogue tasks. Our analysis reveals that InstructDial enables good zero-shot performance on unseen datasets and tasks such as dialogue evaluation and intent detection, and even better performance in a few-shot setting. To ensure that models adhere to instructions, we introduce novel meta-tasks. We establish benchmark zero-shot and few-shot performance of models trained using the proposed framework on multiple dialogue tasks.
Dial_T0
T5-xl 3B type model trained on InstructDial tasks. This model is a fine-tuned version of bigscience/T0_3B model
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
All tasks in InstructDial framework (including all dialogue eval tasks)
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 9
- eval_batch_size: 9
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 72
- total_eval_batch_size: 72
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.3.2
- Tokenizers 0.12.1
- Downloads last month
- 4