Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
MixPoet
Search
Zhang Yixiao
April 30, 2020
Research
4
390
MixPoet
Zhang Yixiao
April 30, 2020
Tweet
Share
More Decks by Zhang Yixiao
See All by Zhang Yixiao
CoCon
ldzhangyx
0
360
vq-cpc
ldzhangyx
0
350
diora
ldzhangyx
0
260
drummernet
ldzhangyx
0
210
ON-LSTM
ldzhangyx
0
160
Other Decks in Research
See All in Research
Time to Cash: The Full Stack Breakdown of Modern ATM Attacks
ratatata
0
130
SSII2025 [TS1] 光学・物理原理に基づく深層画像生成
ssii
PRO
4
4.2k
AWSで実現した大規模日本語VLM学習用データセット "MOMIJI" 構築パイプライン/buiding-momiji
studio_graph
2
520
機械学習と数理最適化の融合 (MOAI) による革新
mickey_kubo
1
320
GPUを利用したStein Particle Filterによる点群6自由度モンテカルロSLAM
takuminakao
0
270
Stealing LUKS Keys via TPM and UUID Spoofing in 10 Minutes - BSides 2025
anykeyshik
0
120
論文読み会 SNLP2025 Learning Dynamics of LLM Finetuning. In: ICLR 2025
s_mizuki_nlp
0
210
引力・斥力を制御可能なランダム部分集合の確率分布
wasyro
0
240
「どう育てるか」より「どう働きたいか」〜スクラムマスターの最初の一歩〜
hirakawa51
0
860
[輪講] SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
nk35jk
2
1k
利用シーンを意識した推薦システム〜SpotifyとAmazonの事例から〜
kuri8ive
1
250
AIグラフィックデザインの進化:断片から統合(One Piece)へ / From Fragment to One Piece: A Survey on AI-Driven Graphic Design
shunk031
0
450
Featured
See All Featured
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
162
15k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
Building an army of robots
kneath
306
46k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
29
1.9k
RailsConf 2023
tenderlove
30
1.2k
Building Applications with DynamoDB
mza
96
6.6k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.4k
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
656
61k
Fireside Chat
paigeccino
39
3.6k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
48
9.7k
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
15
1.7k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
507
140k
Transcript
MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space
ArXiv: 2003.06094v1 Presenter: Yixiao Zhang
Overview • Idea: 诗人经历、历史背景等 => 诗歌风格多样化 • Methods: • semi-supervised
VAE • disentangling latent space to sub-spaces • each sub-space corresponds to one factor conditioning • adversarial training
Introduction • 近年的研究,主要考虑语义连贯、主题相关 • 存在diversity的困扰 • diversity: • 主题间多样性:给定两个topic words,生成不同的诗歌
• 主题内多样性:给定一个topic word,生成不同的诗歌 • * 现有的模型倾向于记住常见pattern
Introduction • 生活经历、历史背景、文学流派 => 影响风格
Introduction • MixPoet: semi-supervised VAE • 将latent space分解为sub-spaces,与影响因子一一对应 • 训练阶段:模型预测无label诗歌的factors
• 测试阶段:指定factor的值,生成风格化的诗歌
Related Work • 诗歌生成模型 (RNNs, Memory Models, etc. ) •
多样性的先前研究: • MRL system: 强化学习,鼓励选用高TF-IDF的词汇 • USPG: 无监督最大化style vector和诗歌的mutual information
Related Work • VAE文本生成/诗歌生成 • Yang et. al, 2018b: 学习context-conditioned
latent variable • Hu et al. 2017: 对生成的诗歌进行对抗训练,增强topic相关性 • CVAE 对话多样性: Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders, ACL 2017 • 本文的对抗:在latent space上做对抗训练
Method • topic keyword: mixture empirical distributions: labeled/ unlabeled
Method: Generator • GRU based model • 是length embedding
Method: Semi-supervised C-VAE • 目的是学习 • 引入z • 由于style与semantics耦合 •
不假设y与z的独立性,而是: • 顺序: w => y => z => x (无y label时)
Method: Semi-supervised C-VAE • then for labeled data: • 估计先验
• 和后验 分别使用一个network计算, recon时最小化KL散度。
Method: Semi-supervised C-VAE • labeled data is too limited •
将y看作另一个latent variable • 估计先验 • 和后验 分别使用一个MLP network计算, recon y时最小化KL散度。
Method: Semi-supervised C-VAE • Total Loss:
Method: Latent Space Mixture • 多个factor时的情形: • 独立性假设:
Method: Latent Space Mixture • How to learn mixed latent
space? • For Isotropic Gaussian Space:
Method: Latent Space Mixture • How to learn mixed latent
space? • For Universal Space: 对于condition: ita是噪声,delta是脉冲函数,c是w, y => 从分布中sample出一个值
Method: Latent Space Mixture • 之后使得discriminator区分这两个z • 估计KL散度: • 其中
就是discriminator
Experiments • factors: • 军旅生涯, 乡村生活, 其他 • 时代繁荣, 时代衰落
• => 6种style
Experiments • Baseline: • Ground Truth • C-VAE • USPG
• MRL: SOTA • fBasic, 监督学习模型
Experiments • 多样性,使用Jaccard Similarity指数评价,越低越好 • 诗歌质量:使用Language Model Score(LMS)评价 • 观察:
• 大多数模型倾向生成重复的短语 • MRL与Basic在intra部分只能生成极其相似的诗歌 • C-VAE情况类似
Experiments • Factor Control Results: • 测试生成的诗歌是否与给定因子类别一致
Experiments • 主观实验
Analysis: Style Mixture
Analysis