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
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Zhang Yixiao
April 30, 2020
Research
4
410
MixPoet
Zhang Yixiao
April 30, 2020
Tweet
Share
More Decks by Zhang Yixiao
See All by Zhang Yixiao
CoCon
ldzhangyx
0
370
vq-cpc
ldzhangyx
0
360
diora
ldzhangyx
0
270
drummernet
ldzhangyx
0
230
ON-LSTM
ldzhangyx
0
180
Other Decks in Research
See All in Research
病院向け生成AIプロダクト開発の実践と課題
hagino3000
0
580
YOLO26_ Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection
satai
3
140
LLMアプリケーションの透明性について
fufufukakaka
0
190
COFFEE-Japan PROJECT Impact Report(海ノ向こうコーヒー)
ontheslope
0
1k
R&Dチームを起ち上げる
shibuiwilliam
1
200
生成的情報検索時代におけるAI利用と認知バイアス
trycycle
PRO
0
390
LiDARセキュリティ最前線(2025年)
kentaroy47
0
280
「なんとなく」の顧客理解から脱却する ──顧客の解像度を武器にするインサイトマネジメント
tajima_kaho
10
7k
Collective Predictive Coding and World Models in LLMs: A System 0/1/2/3 Perspective on Hierarchical Physical AI (IEEE SII 2026 Plenary Talk)
tanichu
1
300
業界横断 副業コンプライアンス調査 三者(副業者・本業先・発注者)におけるトラブル認知ギャップの構造分析
fkske
0
1.2k
AIを叩き台として、 「検証」から「共創」へと進化するリサーチ
mela_dayo
0
160
台湾モデルに学ぶ詐欺広告対策:市民参加の必要性
dd2030
0
260
Featured
See All Featured
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3.3k
Marketing to machines
jonoalderson
1
5k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
508
140k
Making the Leap to Tech Lead
cromwellryan
135
9.8k
brightonSEO & MeasureFest 2025 - Christian Goodrich - Winning strategies for Black Friday CRO & PPC
cargoodrich
3
120
Build your cross-platform service in a week with App Engine
jlugia
234
18k
We Have a Design System, Now What?
morganepeng
55
8k
Why You Should Never Use an ORM
jnunemaker
PRO
61
9.8k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
133
19k
Are puppies a ranking factor?
jonoalderson
1
3.1k
The Illustrated Children's Guide to Kubernetes
chrisshort
51
52k
Primal Persuasion: How to Engage the Brain for Learning That Lasts
tmiket
0
290
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