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
4
410
MixPoet
Zhang Yixiao
April 30, 2020
Tweet
Share
More Decks by Zhang Yixiao
See All by Zhang Yixiao
CoCon
ldzhangyx
0
370
vq-cpc
ldzhangyx
0
360
diora
ldzhangyx
0
270
drummernet
ldzhangyx
0
230
ON-LSTM
ldzhangyx
0
180
Other Decks in Research
See All in Research
学習型データ構造:機械学習を内包する新しいデータ構造の設計と解析
matsui_528
6
3.5k
音声感情認識技術の進展と展望
nagase
0
500
Multi-Agent Large Language Models for Code Intelligence: Opportunities, Challenges, and Research Directions
fatemeh_fard
0
130
HoliTracer:Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery
satai
3
690
教師あり学習と強化学習で作る 最強の数学特化LLM
analokmaus
2
920
[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
290
COFFEE-Japan PROJECT Impact Report(海ノ向こうコーヒー)
ontheslope
0
410
Upgrading Multi-Agent Pathfinding for the Real World
kei18
0
300
[IBIS 2025] 深層基盤モデルのための強化学習驚きから理論にもとづく納得へ
akifumi_wachi
19
9.7k
20251023_くまもと21の会例会_「車1割削減、渋滞半減、公共交通2倍」をめざして.pdf
trafficbrain
0
190
Tiaccoon: Unified Access Control with Multiple Transports in Container Networks
hiroyaonoe
0
780
ペットのかわいい瞬間を撮影する オートシャッターAIアプリへの スマートラベリングの適用
mssmkmr
0
330
Featured
See All Featured
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
10k
Making the Leap to Tech Lead
cromwellryan
135
9.7k
Music & Morning Musume
bryan
47
7.1k
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
460
Neural Spatial Audio Processing for Sound Field Analysis and Control
skoyamalab
0
190
AI: The stuff that nobody shows you
jnunemaker
PRO
3
320
Intergalactic Javascript Robots from Outer Space
tanoku
273
27k
For a Future-Friendly Web
brad_frost
183
10k
Data-driven link building: lessons from a $708K investment (BrightonSEO talk)
szymonslowik
1
930
Evolving SEO for Evolving Search Engines
ryanjones
0
140
The Straight Up "How To Draw Better" Workshop
denniskardys
239
140k
Stewardship and Sustainability of Urban and Community Forests
pwiseman
0
130
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