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
Zhang Yixiao
April 30, 2020
Research
4
390
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
210
ON-LSTM
ldzhangyx
0
170
Other Decks in Research
See All in Research
[RSJ25] Enhancing VLA Performance in Understanding and Executing Free-form Instructions via Visual Prompt-based Paraphrasing
keio_smilab
PRO
0
150
不確実性下における目的と手段の統合的探索に向けた連続腕バンディットの応用 / iot70_gp_rff_mab
monochromegane
2
200
「どう育てるか」より「どう働きたいか」〜スクラムマスターの最初の一歩〜
hirakawa51
0
980
【輪講資料】Moshi: a speech-text foundation model for real-time dialogue
hpprc
3
770
能動適応的実験計画
masakat0
2
900
MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation
satai
4
360
EOGS: Gaussian Splatting for Efficient Satellite Image Photogrammetry
satai
4
730
論文紹介:Not All Tokens Are What You Need for Pretraining
kosuken
0
200
J-RAGBench: 日本語RAGにおける Generator評価ベンチマークの構築
koki_itai
0
860
問いを起点に、社会と共鳴する知を育む場へ
matsumoto_r
PRO
0
670
説明可能な機械学習と数理最適化
kelicht
0
300
Submeter-level land cover mapping of Japan
satai
3
460
Featured
See All Featured
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
2
190
Practical Orchestrator
shlominoach
190
11k
Bash Introduction
62gerente
615
210k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
508
140k
How To Stay Up To Date on Web Technology
chriscoyier
791
250k
GraphQLの誤解/rethinking-graphql
sonatard
73
11k
Stop Working from a Prison Cell
hatefulcrawdad
272
21k
Optimising Largest Contentful Paint
csswizardry
37
3.5k
Build your cross-platform service in a week with App Engine
jlugia
234
18k
How to Ace a Technical Interview
jacobian
280
24k
Being A Developer After 40
akosma
91
590k
What's in a price? How to price your products and services
michaelherold
246
12k
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