Vivi-poem-generation

薇薇：会写诗的机器人

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

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

vivi 1.0 图灵测试结果

论文

Song Iambics Generation with Neural Attention-based Model, IJCAI2016

LNCS, vol 10023, pp.171-183.