"dgl_sparse/vscode:/vscode.git/clone" did not exist on "da1d5de2f16d2f0dc04589c5569d7afaaf1f486b"
Commit 0fa7d87e authored by zihanl's avatar zihanl
Browse files

update README.md

parent 6fc1b02f
...@@ -9,11 +9,11 @@ Blow we present the steps to run our multi-stage dialogue prompting (MSDP) frame ...@@ -9,11 +9,11 @@ Blow we present the steps to run our multi-stage dialogue prompting (MSDP) frame
1. Dataset Download: [Wizard of Wikipedia](https://parl.ai/projects/wizard_of_wikipedia/) and [Wizard of Internet](https://parl.ai/projects/sea/) 1. Dataset Download: [Wizard of Wikipedia](https://parl.ai/projects/wizard_of_wikipedia/) and [Wizard of Internet](https://parl.ai/projects/sea/)
2. Data Processing: We provide script [`tasks/knwl_dialo/scripts/data_processing.sh`](./scripts/data_processing.sh) to process the data. 2. Data Processing: We provide script [`tasks/knwl_dialo/scripts/data_processing.sh`](./scripts/data_processing.sh) to process the data.
### Knowledge Generation ### Stage-1: Prompting for Knowledge Generation
1. The script [`tasks/knwl_dialo/scripts/prompt_knwl_gen.sh`](./scripts/prompt_knwl_gen.sh) provides an example for how to perform the first-stage prompting for the knowledge generation. 1. The script [`tasks/knwl_dialo/scripts/prompt_knwl_gen.sh`](./scripts/prompt_knwl_gen.sh) provides an example for how to perform the first-stage prompting for the knowledge generation.
2. The F1/FK1 score can be evaluated through [`tasks/knwl_dialo/scripts/eval_generation.sh`](./scripts/eval_generation.sh). Other automatic metrics (i.e., BLEU, METEOR, and ROUGE-L) follow the [nlg-eval](https://github.com/Maluuba/nlg-eval). 2. The F1/FK1 score can be evaluated through [`tasks/knwl_dialo/scripts/eval_generation.sh`](./scripts/eval_generation.sh). Other automatic metrics (i.e., BLEU, METEOR, and ROUGE-L) follow the [nlg-eval](https://github.com/Maluuba/nlg-eval).
### Response Generation ### Stage-2: Propmting for Response Generation
1. The script [`tasks/knwl_dialo/scripts/prep_resp_gen.sh`](./scripts/prep_resp_gen.sh) helps to prepare the input file for the response generation (based on the previously generated knowledge file). 1. The script [`tasks/knwl_dialo/scripts/prep_resp_gen.sh`](./scripts/prep_resp_gen.sh) helps to prepare the input file for the response generation (based on the previously generated knowledge file).
2. The script [`tasks/knwl_dialo/scripts/prompt_resp_gen.sh`](./scripts/prompt_resp_gen.sh) provides an example for how to perform the second-stage prompting for the response generation. 2. The script [`tasks/knwl_dialo/scripts/prompt_resp_gen.sh`](./scripts/prompt_resp_gen.sh) provides an example for how to perform the second-stage prompting for the response generation.
3. The automatic evaluations are the same as mentioned aboved for the knowledge generation. 3. The automatic evaluations are the same as mentioned aboved for the knowledge generation.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment