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
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
240
Other Decks in Research
See All in Research
MIRU2026 チュートリアル講演2:三次元データ処理の動向
nnchiba
6
4.9k
横浜市長(山中氏)の言動にかかる第三者による調査報告書
y150saya
0
340
ふとした出会いで生まれたSkillが、 社内利用1位になるまで
mikimhk
21
24k
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
Cross-Media Human-Information Interaction
signer
PRO
0
240
実例から見るLLMのマンガ理解:実務VQAタスクによる長期的文脈と視覚情報の定性評価
kzmssk
0
140
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
某助成金プロジェクト採択に向けて企業研究所のアウトリーチ専任者がやったこと
afroscript
0
180
プレイス・ワークショップ秋葉原
izumiyama_lab
1
100
[Fishers] DIVER OSINT CTF 2026 特化AIエージェントハーネスで挑戦するOSINT CTF
analokmaus
0
580
データサイエンティストの就労意識~2015 → 2026 一般(個人)会員アンケートより
datascientistsociety
PRO
0
810
PHTalks Bengaluru - SSRF When All Else Fails
dk999
0
1.1k
Featured
See All Featured
Crafting Experiences
bethany
1
340
Digital Ethics as a Driver of Design Innovation
axbom
PRO
1
420
Deep Space Network (abreviated)
tonyrice
0
310
We Analyzed 250 Million AI Search Results: Here's What I Found
joshbly
1
1.9k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
12
1.3k
StorybookのUI Testing Handbookを読んだ
zakiyama
31
6.9k
Redefining SEO in the New Era of Traffic Generation
szymonslowik
1
420
jQuery: Nuts, Bolts and Bling
dougneiner
66
8.6k
The Power of CSS Pseudo Elements
geoffreycrofte
82
6.6k
Reflections from 52 weeks, 52 projects
jeffersonlam
356
21k
Mind Mapping
helmedeiros
1
360
Design in an AI World
tapps
1
320
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