Update README.md
Browse files
README.md
CHANGED
|
@@ -99,7 +99,10 @@ We randomly choose 100 sentences from each language to serve as a validation set
|
|
| 99 |
## Usage
|
| 100 |
|
| 101 |
The current model can be used for further fine-tuning on downstream tasks.
|
| 102 |
-
In the paper, we focused on entity-related tasks, such as NER, Word Sense Disambiguation
|
|
|
|
|
|
|
|
|
|
| 103 |
|
| 104 |
## How to Get Started with the Model
|
| 105 |
|
|
|
|
| 99 |
## Usage
|
| 100 |
|
| 101 |
The current model can be used for further fine-tuning on downstream tasks.
|
| 102 |
+
In the paper, we focused on entity-related tasks, such as NER, Word Sense Disambiguation and Slot Filling.
|
| 103 |
+
|
| 104 |
+
Alternatively, it can be used directly (no fine-tuning) for probing tasks, i.e. predict missing words, such as [X-FACTR](https://aclanthology.org/2020.emnlp-main.479/).
|
| 105 |
+
|
| 106 |
|
| 107 |
## How to Get Started with the Model
|
| 108 |
|