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
Emo2Vec: Learning Generalized Emotion Represent...
Search
Yuto Kamiwaki
February 05, 2019
Research
0
120
Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training
2019/02/06 文献紹介の発表内容
Yuto Kamiwaki
February 05, 2019
Tweet
Share
More Decks by Yuto Kamiwaki
See All by Yuto Kamiwaki
Modeling Naive Psychology of Characters in Simple Commonsense Stories
yuto_kamiwaki
1
220
Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm
yuto_kamiwaki
0
110
Epita at SemEval-2018 Task 1: Sentiment Analysis Using Transfer Learning Approach
yuto_kamiwaki
0
140
Tensor Fusion Network for Multimodal Sentiment Analysis
yuto_kamiwaki
0
270
Sentiment Analysis: It’s Complicated!
yuto_kamiwaki
0
86
ADAPT at IJCNLP-2017 Task 4: A Multinomial Naive Bayes Classification Approach for Customer Feedback Analysis task
yuto_kamiwaki
0
180
EmoWordNet: Automatic Expansion of Emotion Lexicon Using English WordNet
yuto_kamiwaki
0
110
ATTENTION-BASED LSTM FOR PSYCHOLOGICAL STRESS DETECTION FROM SPOKEN LANGUAGE USING DISTANT SUPERVISION
yuto_kamiwaki
0
150
BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs
yuto_kamiwaki
0
250
Other Decks in Research
See All in Research
svc-hook: hooking system calls on ARM64 by binary rewriting
retrage
1
100
生成的情報検索時代におけるAI利用と認知バイアス
trycycle
PRO
0
290
Thirty Years of Progress in Speech Synthesis: A Personal Perspective on the Past, Present, and Future
ktokuda
0
160
ウェブ・ソーシャルメディア論文読み会 第36回: The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents (EMNLP, 2025)
hkefka385
0
150
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
140
[Devfest Incheon 2025] 모두를 위한 친절한 언어모델(LLM) 학습 가이드
beomi
2
1.4k
HU Berlin: Industrial-Strength Natural Language Processing with spaCy and Prodigy
inesmontani
PRO
0
220
CoRL2025速報
rpc
4
4.2k
存立危機事態の再検討
jimboken
0
240
HoliTracer:Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery
satai
3
620
ACL読み会2025: Can Language Models Reason about Individualistic Human Values and Preferences?
yukizenimoto
0
120
第66回コンピュータビジョン勉強会@関東 Epona: Autoregressive Diffusion World Model for Autonomous Driving
kentosasaki
0
340
Featured
See All Featured
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
37
6.3k
Bioeconomy Workshop: Dr. Julius Ecuru, Opportunities for a Bioeconomy in West Africa
akademiya2063
PRO
1
54
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
54k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
9.9k
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
2
420
The State of eCommerce SEO: How to Win in Today's Products SERPs - #SEOweek
aleyda
2
9.5k
Designing for Timeless Needs
cassininazir
0
130
XXLCSS - How to scale CSS and keep your sanity
sugarenia
249
1.3M
Everyday Curiosity
cassininazir
0
130
Have SEOs Ruined the Internet? - User Awareness of SEO in 2025
akashhashmi
0
270
StorybookのUI Testing Handbookを読んだ
zakiyama
31
6.6k
A better future with KSS
kneath
240
18k
Transcript
Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training Nagaoka University
of Technology Yuto Kamiwaki Literature Review
Literature • Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training
• Peng Xu, Andrea Madotto, Chien-Sheng Wu, Ji Ho Park and Pascale Fung • Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, 2018 2
3 • 気圧が変化すると頭が痛い. • あなたのことを考えると頭が痛い.
Introduction 4 通常のWord embeddingで捉えられる: • 発熱 • 頭痛 • 歯痛
通常のWord embeddingで捉えられない: • あなたのことを考えると頭が痛い. 意味の近さは,捉えられる.
• 感情的な意味をベクトル化するEmo2Vecを提案. • 既存の手法(SSWE,DeepMoji)よりも良い結果. • GloVeと組み合わせると単純なロジスティック回帰分類器で いくつかのタスクのSoTAに匹敵する. 5
6
7
8
9 データ規模 Train[%] validation[%] test[%] Twitterのデータ 190万文 70 15 15
learning rate : 0.001 L2 regularization : 1.0 batch size
: 32 ベースラインとしてSSWE,DeepMojiを使用. • SSWE 50次元のセンチメント固有のWord embedding 意味情報と感情情報の両方をベクトルに符号化することによって1000万ツイート を学習した埋め込みモデル • DeepMoji 12億のツイートの巨大なデータセットを使って入力文書の絵文字を予測するモデ ル.埋め込み層は,暗黙のうちに感情の知識で符号化されている. DeepMojiの256次元埋め込み層であるDeepMojiのWord embedingを使用. 10 最良のモデルを保存し, 埋め込み層をEmo2Vecの ベクトルとして使用.
11
12
Conclusion • マルチタスクトレーニングフレームワークを用いて感情をベク トルで表現するEmo2Vecを提案. • 10を超える異なるデータセットに対する既存の心理関連の Word embeddingよりも優れている. • Emo2VecとGloVeを組み合わせることで,ロジスティック回
帰はいくつかのSoTAと互角の性能. 13