studio-ousia
/

luke-japanese-base

named entity recognition

relation classification

question answering

Inference Endpoints

Model card Files Files and versions Community

ikuyamada commited on Oct 26, 2022

Commit

3ff7a5a

•

1 Parent(s): 08a09af

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -28,7 +28,7 @@ The experimental results evaluated on the dev set of
 | Model                  | MARC-ja   | JSTS                | JNLI      | JCommonsenseQA |
 | ---------------------- | --------- | ------------------- | --------- | -------------- |
 |                        | acc       | Pearson/Spearman    | acc       | acc            |
-| **LUKE Japanese base** | **0.963** | **0.912**/**0.875** | **0.912** | **0.842**      |
 | _Baselines:_           |           |
 | Tohoku BERT base       | 0.958     | 0.899/0.859         | 0.899     | 0.808          |
 | NICT BERT base         | 0.958     | 0.903/0.867         | 0.902     | 0.823          |

 | Model                  | MARC-ja   | JSTS                | JNLI      | JCommonsenseQA |
 | ---------------------- | --------- | ------------------- | --------- | -------------- |
 |                        | acc       | Pearson/Spearman    | acc       | acc            |
+| **LUKE Japanese base** | **0.965** | **0.912**/**0.875** | **0.912** | **0.842**      |
 | _Baselines:_           |           |
 | Tohoku BERT base       | 0.958     | 0.899/0.859         | 0.899     | 0.808          |
 | NICT BERT base         | 0.958     | 0.903/0.867         | 0.902     | 0.823          |