Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
Using millions of emoji occurrences to learn an...
Search
Yuto Kamiwaki
December 16, 2018
Research
130
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
150
Tensor Fusion Network for Multimodal Sentiment Analysis
yuto_kamiwaki
0
290
Sentiment Analysis: It’s Complicated!
yuto_kamiwaki
0
96
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
170
BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs
yuto_kamiwaki
0
270
Other Decks in Research
See All in Research
論文紹介:Doc-to-LoRA: Learning to Instantly Internalize Contexts
yukako_nakano
0
180
Evaluating LLM Reliability Across Facts, Evidence, and Cultures
yukiar
0
180
Anthropic が提案する LLM の内部状態を自然言語で説明可能にした Natural Language Autoencoders / Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations
shunk031
0
290
OWASP AISVS - C7
shiell
2
790
[Fishers] DIVER OSINT CTF 2026 特化AIエージェントハーネスで挑戦するOSINT CTF
analokmaus
0
610
論文紹介: Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mind
hisaokatsumi
0
170
量子サマースクール2026「量子計算機アーキテクチャ分野の概観」
youten622
1
930
Karkada さんの論文 × 2 の紹介: (1) Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models, (2) Symmetry in language statistics shapes the geometry of model representations
eumesy
PRO
1
770
HAKARI-Bench - 実運用視点での情報検索モデル評価ベンチマーク
hotchpotch
1
770
Kaggle|AI Agent Security — しくじり先生、俺みたいになるな
pomcho555
1
100
学術バーQ AI研究最前線:自己教師あり学習による画像モデルの事前学習
naok615
0
110
Apache Gravitinoで実現する Icebergカタログ統合とアクセスの一元化
matsumooon
0
540
Featured
See All Featured
The B2B funnel & how to create a winning content strategy
katarinadahlin
PRO
1
540
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
340
Art, The Web, and Tiny UX
lynnandtonic
304
22k
The AI Search Optimization Roadmap by Aleyda Solis
aleyda
1
6.2k
SERP Conf. Vienna - Web Accessibility: Optimizing for Inclusivity and SEO
sarafernandez
2
1.6k
Automating Front-end Workflow
addyosmani
1369
210k
Java REST API Framework Comparison - PWX 2021
mraible
34
9.7k
Neural Spatial Audio Processing for Sound Field Analysis and Control
skoyamalab
0
520
Applied NLP in the Age of Generative AI
inesmontani
PRO
4
2.5k
How Software Deployment tools have changed in the past 20 years
geshan
1
34k
The browser strikes back
jonoalderson
0
1.7k
Agile that works and the tools we love
rasmusluckow
331
22k
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