“Vivi-poem-generation”版本间的差异
来自cslt Wiki
| （1位用户的7个中间修订版本未显示） | |||
| 第1行： | 第1行： | ||
=薇薇：会写诗的机器人= | =薇薇：会写诗的机器人= | ||
| + | |||
| + | 成员：王东，王琪鑫，骆天一，张纪袁，冯洋 | ||
==vivi 3.0 (on going) == | ==vivi 3.0 (on going) == | ||
| 第39行： | 第41行： | ||
===论文=== | ===论文=== | ||
| − | + | * [https://arxiv.org/abs/1705.03773 Creative generation of poems] | |
==vivi 1.0== | ==vivi 1.0== | ||
| 第55行： | 第57行： | ||
===测试结果=== | ===测试结果=== | ||
| − | [[中国古诗词图灵测试|vivi 1.0 图灵测试结果]] | + | * [[中国古诗词图灵测试|vivi 1.0 图灵测试结果]] |
===论文=== | ===论文=== | ||
| − | [https://arxiv.org/abs/1604.06274|Chinese Song Iambics Generation with Neural Attention-based Model, IJCAI2016] | + | * [https://arxiv.org/abs/1604.06274|Chinese Song Iambics Generation with Neural Attention-based Model, IJCAI2016] |
| + | |||
| + | * [http://link.springer.com/chapter/10.1007/978-3-319-49685-6_4/fulltext.html|Can Machine Generate Traditional Chinese Poetry? A Feigenbaum Test, Springer, LNCS, vol 10023, pp.171-183.] | ||
| + | |||
| + | * [https://arxiv.org/abs/1705.03773 Jiyuan Zhang, Yang Feng, Dong Wang, Yang Wang, Andrew Abel, Shiyue Zhang, Andi Zhangi, "Flexible and Creative Chinese Poetry Generation Using Neural Memory"] | ||
| + | |||
| + | |||
| + | ===文章=== | ||
| − | [ | + | [[Wangd-wiki-article-vvpoem|薇薇的故事]] |
2018年7月24日 (二) 17:05的最后版本
目录
薇薇：会写诗的机器人
成员：王东，王琪鑫，骆天一，张纪袁，冯洋
vivi 3.0 (on going)
目标
- Transfer modern sentences to poems
- Utilize extra knowledge to boost innovation
- Reinforcement learning to improve quality
vivi 2.0
基本方法
- Tensorflow 实现
- Attention-based LSTM/GRU S2S
- Sampling words as input to generate the present sentence
- Memory augmentation (global and local)
- Local attention for theme (+)
- Local attention on previous generation, with couplet assignment （line number?） (+)
- N-best decoding (+)
实现细节
- Rythms with less characters removed
- Characters seldom used as rhythms words are removed
- Characters that are low-frequency are removed
特性
- 训练基础模型，用memory实现精细创新
- 用memory可实现风格、体例转换
- 用Local attention可实现人为指导创作（+）
- 可实现律诗中的对仗
测试结果
论文
vivi 1.0
基本方法
- Theano 实现
- 基于sequence-to-sequence的LSTM/GRU模型, 运用Attention 机制。
- 输入为一首诗的第一句，输出为后面所有句子
- 预训练word vectors，用多种体例古文结合在一起训练
- 生成时可对用户输入进行扩展
测试结果
论文
