Commit
·
0efa5e3
1
Parent(s):
601b153
Update README.md
Browse files
README.md
CHANGED
@@ -21,6 +21,10 @@ LUKE (Language Understanding with Knowledge-based Embeddings) is a new pre-train
|
|
21 |
LUKE achieves state-of-the-art results on five popular NLP benchmarks including SQuAD v1.1 (extractive question answering), CoNLL-2003 (named entity recognition), ReCoRD (cloze-style question answering), TACRED (relation classification), and Open Entity (entity typing).
|
22 |
|
23 |
# how to use 使い方
|
|
|
|
|
|
|
|
|
24 |
-------------------------------------------------------------
|
25 |
|
26 |
import torch
|
|
|
21 |
LUKE achieves state-of-the-art results on five popular NLP benchmarks including SQuAD v1.1 (extractive question answering), CoNLL-2003 (named entity recognition), ReCoRD (cloze-style question answering), TACRED (relation classification), and Open Entity (entity typing).
|
22 |
|
23 |
# how to use 使い方
|
24 |
+
出力としてはpre.logitsが得られます。
|
25 |
+
pre.logitsはtensor[[x,y]]というテンソルになっています。
|
26 |
+
num = SOFTMAX(pre.logits)にすることで、num[0]がネガティブである確率、num[1]がポジティブである確率を表すようになります。
|
27 |
+
|
28 |
-------------------------------------------------------------
|
29 |
|
30 |
import torch
|