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
400
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
220
ON-LSTM
ldzhangyx
0
170
Other Decks in Research
See All in Research
Panopticon: Advancing Any-Sensor Foundation Models for Earth Observation
satai
3
340
Nullspace MPC
mizuhoaoki
1
390
SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images
satai
3
420
SNLP2025:Can Language Models Reason about Individualistic Human Values and Preferences?
yukizenimoto
0
210
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
590
2025/7/5 応用音響研究会招待講演@北海道大学
takuma_okamoto
1
230
とあるSREの博士「過程」 / A Certain SRE’s Ph.D. Journey
yuukit
11
4.9k
超高速データサイエンス
matsui_528
1
210
能動適応的実験計画
masakat0
2
1k
その推薦システムの評価指標、ユーザーの感覚とズレてるかも
kuri8ive
1
250
第二言語習得研究における 明示的・暗示的知識の再検討:この分類は何に役に立つか,何に役に立たないか
tam07pb915
0
370
湯村研究室の紹介2025 / yumulab2025
yumulab
0
180
Featured
See All Featured
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
48
9.8k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
17k
How STYLIGHT went responsive
nonsquared
100
5.9k
GitHub's CSS Performance
jonrohan
1032
470k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
26
3.2k
Code Reviewing Like a Champion
maltzj
527
40k
GraphQLとの向き合い方2022年版
quramy
49
14k
The Illustrated Children's Guide to Kubernetes
chrisshort
51
51k
Building a Scalable Design System with Sketch
lauravandoore
463
34k
4 Signs Your Business is Dying
shpigford
186
22k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
253
22k
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
10
690
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