shibing624
commited on
Commit
•
27a63b7
1
Parent(s):
cd8faa3
Update README.md
Browse files
README.md
CHANGED
@@ -13,15 +13,15 @@ widget:
|
|
13 |
---
|
14 |
|
15 |
# SongNet for Chinese Couplet(songnet-base-chinese-couplet) Model
|
16 |
-
SongNet
|
17 |
|
18 |
`songnet-base-chinese-couplet` evaluate couplet test data:
|
19 |
|
20 |
-
The overall performance of
|
21 |
|
22 |
-
|input_text|
|
23 |
-
|:--- |:---
|
24 |
-
|
25 |
|
26 |
在Couplet测试集上生成结果满足字数相同、词性对齐、词面对齐、形似要求,针对性的SongNet网络结构,在语义对仗工整和平仄合律上的效果明显优于T5和GPT2等模型。
|
27 |
|
@@ -61,9 +61,15 @@ sentences = [
|
|
61 |
]
|
62 |
print("inputs:", sentences)
|
63 |
print("outputs:", model.fill_mask(sentences))
|
64 |
-
|
65 |
```
|
66 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
|
68 |
模型文件组成:
|
69 |
```
|
|
|
13 |
---
|
14 |
|
15 |
# SongNet for Chinese Couplet(songnet-base-chinese-couplet) Model
|
16 |
+
SongNet中文对联仿写模型
|
17 |
|
18 |
`songnet-base-chinese-couplet` evaluate couplet test data:
|
19 |
|
20 |
+
The overall performance of SongNet on couplet **test**:
|
21 |
|
22 |
+
|input_text|predict|
|
23 |
+
|:--- |:--- |
|
24 |
+
|一句相思吟岁月</s>千杯美酒醉风情|<bos>一生只剩诗和酒</s>满腹无关雪与梅</s>|
|
25 |
|
26 |
在Couplet测试集上生成结果满足字数相同、词性对齐、词面对齐、形似要求,针对性的SongNet网络结构,在语义对仗工整和平仄合律上的效果明显优于T5和GPT2等模型。
|
27 |
|
|
|
61 |
]
|
62 |
print("inputs:", sentences)
|
63 |
print("outputs:", model.fill_mask(sentences))
|
|
|
64 |
```
|
65 |
|
66 |
+
output:
|
67 |
+
```shell
|
68 |
+
inputs: ['严蕊<s1>如梦令<s2>道是梨花不是。</s>道是杏花不是。</s>白白与红红,别是东风情味。</s>曾记。</s>曾记。</s>人在武陵微醉。', '<s1><s2>一句相思吟岁月</s>千杯美酒醉风情', '<s1><s2>几树梅花数竿竹</s>一潭秋水半屏山<s1><s2>未舍东江开口咏</s>且施妙手点睛来', '<s1><s2>一去二三里</s>烟村四五家']
|
69 |
+
outputs: ['<bos>盛世欣开新气象</s>春联喜绘大文章</s>春天铺锦笺,宏图更写好山山</s>新篇章</s>新篇章</s>神州高唱好年华</s>', '<bos>一曲琴音添雅韵</s>几回酒醉解愁思</s>', '<bos>三分天下隆中对</s>四面八方九派江山笔底留</s>', '<bos>春深花已老</s>夜静露方浓</s>']
|
70 |
+
inputs: ['<s1><s2>一句____月</s>千杯美酒__情', '<s1><s2>一去二三里</s>烟村__家</s>亭台__座</s>八__枝花']
|
71 |
+
outputs: ['<bos>一句佳诗吟盛月</s>千杯美酒祝春情</s>', '<bos>一去二三里</s>烟村百二家</s>亭台十二座</s>八里一枝花</s>']
|
72 |
+
```
|
73 |
|
74 |
模型文件组成:
|
75 |
```
|