$30 off During Our Annual Pro Sale. View Details »
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
MixPoet
Search
Zhang Yixiao
April 30, 2020
Research
4
400
MixPoet
Zhang Yixiao
April 30, 2020
Tweet
Share
More Decks by Zhang Yixiao
See All by Zhang Yixiao
CoCon
ldzhangyx
0
360
vq-cpc
ldzhangyx
0
350
diora
ldzhangyx
0
260
drummernet
ldzhangyx
0
230
ON-LSTM
ldzhangyx
0
170
Other Decks in Research
See All in Research
生成AI による論文執筆サポート・ワークショップ ─ サーベイ/リサーチクエスチョン編 / Workshop on AI-Assisted Paper Writing Support: Survey/Research Question Edition
ks91
PRO
0
120
EcoWikiRS: Learning Ecological Representation of Satellite Images from Weak Supervision with Species Observation and Wikipedia
satai
3
460
Panopticon: Advancing Any-Sensor Foundation Models for Earth Observation
satai
3
430
GPUを利用したStein Particle Filterによる点群6自由度モンテカルロSLAM
takuminakao
0
650
説明可能な機械学習と数理最適化
kelicht
2
750
CoRL2025速報
rpc
3
3.6k
自動運転におけるデータ駆動型AIに対する安全性の考え方 / Safety Engineering for Data-Driven AI in Autonomous Driving Systems
ishikawafyu
0
110
Tiaccoon: Unified Access Control with Multiple Transports in Container Networks
hiroyaonoe
0
140
若手研究者が国際会議(例えばIROS)でワークショップを企画するメリットと成功法!
tanichu
0
120
Remote sensing × Multi-modal meta survey
satai
4
640
離散凸解析に基づく予測付き離散最適化手法 (IBIS '25)
taihei_oki
PRO
1
630
Language Models Are Implicitly Continuous
eumesy
PRO
0
360
Featured
See All Featured
Testing 201, or: Great Expectations
jmmastey
46
7.8k
Technical Leadership for Architectural Decision Making
baasie
0
180
How to Align SEO within the Product Triangle To Get Buy-In & Support - #RIMC
aleyda
1
1.3k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.6k
Test your architecture with Archunit
thirion
1
2.1k
Digital Projects Gone Horribly Wrong (And the UX Pros Who Still Save the Day) - Dean Schuster
uxyall
0
100
16th Malabo Montpellier Forum Presentation
akademiya2063
PRO
0
22
Gemini Prompt Engineering: Practical Techniques for Tangible AI Outcomes
mfonobong
2
220
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
141
34k
Efficient Content Optimization with Google Search Console & Apps Script
katarinadahlin
PRO
0
240
Visual Storytelling: How to be a Superhuman Communicator
reverentgeek
2
390
Lightning Talk: Beautiful Slides for Beginners
inesmontani
PRO
1
400
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