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
Using millions of emoji occurrences to learn an...
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Yuto Kamiwaki
December 16, 2018
Research
120
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm
2018/12/17 文献紹介の発表内容
Yuto Kamiwaki
December 16, 2018
More Decks by Yuto Kamiwaki
See All by Yuto Kamiwaki
Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training
yuto_kamiwaki
0
120
Modeling Naive Psychology of Characters in Simple Commonsense Stories
yuto_kamiwaki
1
220
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
280
Sentiment Analysis: It’s Complicated!
yuto_kamiwaki
0
93
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
120
ATTENTION-BASED LSTM FOR PSYCHOLOGICAL STRESS DETECTION FROM SPOKEN LANGUAGE USING DISTANT SUPERVISION
yuto_kamiwaki
0
160
BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs
yuto_kamiwaki
0
260
Other Decks in Research
See All in Research
CyberAgent AI Lab研修 / Social Implementation Anti-Patterns in AI Lab
chck
7
4.7k
論文紹介 "ReSim: Reliable World Simulation for Autonomous Driving"
kogo
0
650
AIエージェント時代のLLM-jpモデルのあるべき姿
k141303
0
480
Data Visualization Tools in the Age of AI
flekschas
0
160
「行ける・行けない表」による地域公共交通の性能評価
bansousha
0
160
Scalable dynamic origin-destination demand estimation enhanced by high-resolution satellite imagery data
satai
3
300
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
shunk031
4
1.1k
衛星×エッジAI勉強会 衛星上におけるAI処理制約とそ取組について
satai
4
570
Sleuthcon Keynote - How Cybercriminals (ab)use AI
fr0gger
0
210
「AIとWhyを深堀る」をAIと深堀る
iflection
0
500
Can We Teach Logical Reasoning to LLMs? – An Approach Using Synthetic Corpora (AAAI 2026 bridge keynote)
morishtr
1
260
シングルチャネルマルチトーカー音声認識の進展
ryomasumura
0
140
Featured
See All Featured
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
28
3.5k
Optimising Largest Contentful Paint
csswizardry
37
3.7k
The Limits of Empathy - UXLibs8
cassininazir
1
370
Navigating the moral maze — ethical principles for Al-driven product design
skipperchong
2
400
Visualization
eitanlees
152
17k
VelocityConf: Rendering Performance Case Studies
addyosmani
333
25k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
Getting science done with accelerated Python computing platforms
jacobtomlinson
2
240
Accessibility Awareness
sabderemane
1
140
Technical Leadership for Architectural Decision Making
baasie
3
420
Being A Developer After 40
akosma
91
590k
Utilizing Notion as your number one productivity tool
mfonobong
4
330
Transcript
Using millions of emoji occurrences to learn any-domain representations for
detecting sentiment, emotion and sarcasm Nagaoka University of Technology Yuto Kamiwaki Literature Review
Literature • Using millions of emoji occurrences to learn any-domain
representations for detecting sentiment, emotion and sarcasm • Bjarke Felbo, Alan Mislove, Anders Søgaard, Iyad Rahwan, Sune Lehmann • EMNLP 2017 2
Abstract • sentiment analysis, emotion analysis and sarcasm classificationにおける8つのbenchmarkでSoTA達成 •
感情ラベルの多様性が以前のdistant supervisonのアプ ローチよりもパフォーマンスの向上をもたらすことを確認 3
Introduction • NLPのタスクでは,アノテーション済み(感情が付与された)の データは少ない. • Distant supervisionを用いてSoTAを達成している研究があ る. Distant supervision
: (http://web.stanford.edu/~jurafsky/mintz.pdf) ラベル付きデータの情報を手がかりに全く別のラベルなしデータからラベル付きの学 習データを生成し、モデルを学習する手法 4
Related work • Ekman, Plutchikなどの感情の理論を用いて手作業によって 分類 ◦ 感情の理解が難しく,時間がかかる. • official
emoji tables (Eisner et al., 2016)からembeddingす る手法 ◦ emojiの使われ方を考慮しない. • マルチタスク学習 ◦ データストレージの観点から問題あり. 5
Pretraining • 2013年1月から2017年6月までのTweet data(emojiあり) • Only English tweets without URL’s
are used for the pretraining dataset. • All tweets are tokenized on a word-by-word basis. 6
Model 7
Transfer Learning(ChainThaw) 8
Emoji Prediction 9
Benchmarking 10 8 Benchmarks(3tasks,5domains)
Benchmarking 11
Importance of emoji diversity 12 Pos/Neg Emoji:8 types DeepMoji:64 types
感情ラベルの多様性が重要 64種類のemojiの細かい ニュアンスを学習できている. (次ページの図を参照)
Importance of emoji diversity 13
Model architecture 14 Pretraining時点では,差がない benchmark時点では,Attention ありの方が精度が高い 低層の特徴へのアクセスが簡単 勾配消失がなく,学習可能
Analyzing the effect of pretraining 15 Pretraining+chainthawで語彙が 増加 ->word coverageが改善
Comparing with human-level agreement 16 Human:76.1% Deepmoji:82.4% Deepmojiの方が,精度 が高い (実験内容については,論文
を参照)
Conclusion • sentiment analysis, emotion analysis and sarcasm classificationにおける8つのbenchmarkでSoTA達成 •
感情ラベルの多様性が以前のdistant supervisonのアプ ローチよりもパフォーマンスの向上をもたらすことを確認 • Pretraining済みモデルを公開 ◦ (Demo : https://deepmoji.mit.edu/) 17