“Vivi-poem-generation”版本间的差异
来自cslt Wiki
(1位用户的2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41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66行: | 第66行: | ||
* [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"] | * [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