From b5ba56cb4c4921ea18d2c3e36aa633343903001f Mon Sep 17 00:00:00 2001 From: Pavan Mandava Date: Sun, 4 Dec 2022 16:55:44 +0100 Subject: [PATCH] Removed latex equation and added TOC --- README.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 2c79f0b..d759c1c 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,7 @@ +--- +gitea: none +include_toc: true +--- # Prompt-based methods for Dialog State Tracking @@ -269,12 +273,8 @@ In the previous section, only a single *value-based* prompt is used at training A separate prompt ensemble model is trained for each data split to evaluate the performance of multi-prompt methods in low-resource scenarios. Edit the [train_prompting.sh](prompt-learning/train_prompting.sh) file to add `--with_prompt_ensemble` flag for training with multiple prompt functions. -The probability of slot $s_{t}$ on multiple prompt functions are calculated using: +The probability of the generated slot (for loss) on multiple prompt functions is calculated by weighted averaging the probability from each prompt function. -$$ -P\left(s_{t} \mid c_{t}\right)=\sum_{k}^{|K|} \alpha_{k} * P\left(s_{t} \mid c_{t}, f_{k}\left(v_{t}\right)\right) -$$ -where $|K|$ represents the number of prompt functions, $f_{k}$ is the $k$-th prompt function, $\alpha_{k}$ is the weight of prompt $k$. The prompt weight $\alpha_{k}$ is set to `0.25` for all prompt functions. The loss $L$ for prompt ensemble training is calculated using the above function. Run the training script as before after adding the `--with_prompt_ensemble` flag: ```shell