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
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
390
vq-cpc
ldzhangyx
0
380
diora
ldzhangyx
0
290
drummernet
ldzhangyx
0
250
ON-LSTM
ldzhangyx
0
210
Other Decks in Research
See All in Research
Apache Gravitinoで実現する Icebergカタログ統合とアクセスの一元化
matsumooon
0
290
適応的スパムフィルタのための軽量な類似メッセージカウンタ / jsai2026-adaptive-spam-filter
monochromegane
0
3.7k
多様なデータを許容し学習し続ける模倣学習 / Advanced Imitation Learning for VLA
prinlab
0
220
2026 東京科学大 情報通信系 研究室紹介 (すずかけ台)
icttitech
0
3.8k
Dual Quadric表現を用いた動的物体追跡とRGB-D・IMU制約の密結合によるオドメトリ推定
nanoshimarobot
0
410
Can We Teach Logical Reasoning to LLMs? – An Approach Using Synthetic Corpora (AAAI 2026 bridge keynote)
morishtr
1
260
Data Visualization Tools in the Age of AI
flekschas
0
160
Any-Optical-Model: A Universal Foundation Model for Optical Remote Sensing
satai
3
840
討議:RACDA設立30周年記念都市交通フォーラム2026
trafficbrain
0
960
NLP colloquium: AI Safety Survey
kanekomasahiro
0
740
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
570
「AIとWhyを深堀る」をAIと深堀る
iflection
0
490
Featured
See All Featured
HDC tutorial
michielstock
2
720
The SEO Collaboration Effect
kristinabergwall1
1
490
Large-scale JavaScript Application Architecture
addyosmani
515
110k
職位にかかわらず全員がリーダーシップを発揮するチーム作り / Building a team where everyone can demonstrate leadership regardless of position
madoxten
62
54k
Docker and Python
trallard
47
3.9k
SEOcharity - Dark patterns in SEO and UX: How to avoid them and build a more ethical web
sarafernandez
0
210
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
10k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
35
3.5k
Keith and Marios Guide to Fast Websites
keithpitt
413
23k
Tell your own story through comics
letsgokoyo
1
960
So, you think you're a good person
axbom
PRO
2
2.1k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
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