Update README.md
Browse files
README.md
CHANGED
@@ -106,7 +106,7 @@ KnowPrompt is used for relational extraction tasks, injecting latent knowledge
|
|
106 |
## Model description
|
107 |
|
108 |
We take the first step to inject latent knowledge contained in relation labels into prompt construction,the knowledge extraction is then implemented with a Prompt-tuning model。The implementation is as follows:virtual template words around entities initialized using aggregate entity embeddings are used as learnable virtual template words to inject entity knowledge; Meanwhile, we leverage label to compute average embeddings as virtual answers words to inject relationship knowledge. In this structure, entities and relations are mutually constrained and virtual template and answer words should be contextually relevant, so we introduce synergistic optimization to correct virtual template and answer words.
|
109 |
-
![image.png](
|
110 |
|
111 |
## Intended uses & limitations
|
112 |
|
|
|
106 |
## Model description
|
107 |
|
108 |
We take the first step to inject latent knowledge contained in relation labels into prompt construction,the knowledge extraction is then implemented with a Prompt-tuning model。The implementation is as follows:virtual template words around entities initialized using aggregate entity embeddings are used as learnable virtual template words to inject entity knowledge; Meanwhile, we leverage label to compute average embeddings as virtual answers words to inject relationship knowledge. In this structure, entities and relations are mutually constrained and virtual template and answer words should be contextually relevant, so we introduce synergistic optimization to correct virtual template and answer words.
|
109 |
+
![image.png](./model.png)
|
110 |
|
111 |
## Intended uses & limitations
|
112 |
|