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
440
4
Share
MixPoet
Zhang Yixiao
April 30, 2020
More Decks by Zhang Yixiao
See All by Zhang Yixiao
CoCon
ldzhangyx
0
380
vq-cpc
ldzhangyx
0
380
diora
ldzhangyx
0
290
drummernet
ldzhangyx
0
240
ON-LSTM
ldzhangyx
0
200
Other Decks in Research
See All in Research
YOLO26_ Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection
satai
3
760
セマンティック通信勉強会 6Gに向けたデバイス間効率的な通信の技術紹介・課題・今後展望
satai
2
130
2026 東京科学大 情報通信系 研究室紹介 (大岡山)
icttitech
0
3.6k
[チュートリアル] 電波マップ構築入門 :研究動向と課題設定の勘所
k_sato
0
450
東京大学工学部計数工学科、計数工学特別講義の説明資料
kikuzo
0
440
Harness Engineering and Al Agent
kzinmr
3
1.6k
正規分布と最適化について
koide3
0
230
非試合日の野球場を楽しむためのARホームランボールキャッチ体験システムの開発 / EC79-miyazaki
yumulab
0
180
NII S. Koyama's Lab Research Overview AY2026
skoyamalab
0
260
英語教育 “研究” のあり方:学術知とアウトリーチの緊張関係
terasawat
1
970
ScoreMatchingRiesz for Automatic Debiased Machine Learning and Policy Path Estimation with an Application to Japanese Monetary Policy Evaluation
masakat0
0
280
AGI4OPT:自然言語から数理最適化を導くエ ージェントスキル Translating Human Intent into Mathematical Optimization
mickey_kubo
0
130
Featured
See All Featured
コードの90%をAIが書く世界で何が待っているのか / What awaits us in a world where 90% of the code is written by AI
rkaga
61
44k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
17k
A Guide to Academic Writing Using Generative AI - A Workshop
ks91
PRO
1
310
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
9
1.4k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
55k
How STYLIGHT went responsive
nonsquared
100
6.1k
Art, The Web, and Tiny UX
lynnandtonic
304
21k
AI: The stuff that nobody shows you
jnunemaker
PRO
7
670
How to Get Subject Matter Experts Bought In and Actively Contributing to SEO & PR Initiatives.
livdayseo
0
130
The Illustrated Children's Guide to Kubernetes
chrisshort
51
52k
Side Projects
sachag
455
43k
Beyond borders and beyond the search box: How to win the global "messy middle" with AI-driven SEO
davidcarrasco
3
150
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