Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
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
470
4
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
MixPoet
Zhang Yixiao
April 30, 2020
More Decks by Zhang Yixiao
See All by Zhang Yixiao
CoCon
ldzhangyx
0
420
vq-cpc
ldzhangyx
0
410
diora
ldzhangyx
0
310
drummernet
ldzhangyx
0
280
ON-LSTM
ldzhangyx
0
230
Other Decks in Research
See All in Research
第64回CV・PRML勉強会 論文紹介:Linguistic Priors for Visual Decoupling: Towards Symmetric Vision-Brain Alignment
sokikatayama
0
190
Visual SLAM未来予測 / Future Prediction in Visual SLAM
koide3
1
1k
Fukui Shibiten 39 - AI Art
butchi
0
190
HAKARI-Bench - 実運用視点での情報検索モデル評価ベンチマーク
hotchpotch
1
740
The story of RefactoringMiner. Slow research, long-term impact
tsantalis
0
150
CVPR2026論文紹介_VLMにとって良いvision encoderとは何か?Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance
kobayashi31
1
210
Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance
satai
3
130
論文紹介: Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mind
hisaokatsumi
0
160
長時間動画QAにおけるマルチエージェント推論 ・SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration
murakawatakuya
1
200
シングルチャネルマルチトーカー音声認識の進展
ryomasumura
0
270
LINEヤフー データサイエンス Meetup「三井物産コモディティ予測チャレンジ」の舞台裏-AlpacaTechパート
gamella
1
660
HackSick vol.7 LT資料【LLMアーキテクチャ入門・事前学習時の躓き所解説】 スパースなAttention・状態空間モデル
rikkabotan7
0
180
Featured
See All Featured
How To Speak Unicorn (iThemes Webinar)
marktimemedia
1
580
Heart Work Chapter 1 - Part 1
lfama
PRO
9
36k
AI in Enterprises - Java and Open Source to the Rescue
ivargrimstad
0
1.5k
The untapped power of vector embeddings
frankvandijk
2
1.9k
The Language of Interfaces
destraynor
162
27k
Designing for Performance
lara
611
70k
Reflections from 52 weeks, 52 projects
jeffersonlam
356
21k
Build The Right Thing And Hit Your Dates
maggiecrowley
39
3.4k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
508
140k
Building a A Zero-Code AI SEO Workflow
portentint
PRO
0
720
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
31
2.9k
What the history of the web can teach us about the future of AI
inesmontani
PRO
1
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