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
文献紹介: A Document Descriptor using Covariance of...
Search
Yumeto Inaoka
February 27, 2019
Research
340
1
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
文献紹介: A Document Descriptor using Covariance of Word Vectors
2019/02/27の文献紹介で発表
Yumeto Inaoka
February 27, 2019
More Decks by Yumeto Inaoka
See All by Yumeto Inaoka
文献紹介: Quantity doesn’t buy quality syntax with neural language models
yumeto
1
230
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
300
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
200
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
220
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
240
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
340
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
440
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
260
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
310
Other Decks in Research
See All in Research
山中市政が招いた組織崩壊:よこはま安心ボックスを例に
sishi
0
370
Détection des lésions podales par thermographie infrarouge chez les bovins et les ovins
institutdelelevage
PRO
0
120
PHTalks Bengaluru - SSRF When All Else Fails
dk999
0
1.2k
ハードウェア研究で国際トップ会議を目指す!IROS 2027での論文採択を目指して
ayatokanada
7
4.2k
Easy to Guess, Hard to Verify: Lessons from AIMO 3 for Olympiad-Level AI Mathematics
corochann
0
150
Top 4セキュリティ会議に一通り論文が採択されるまでの道のりと展望 / Top 4 Security Grand Slam
takaomurakami
0
1.1k
Bilan travail en élevage : première restitution des enquêtes 2025-2026
institutdelelevage
PRO
0
170
Méthane 2030 : Développer des solutions de réduction des émissions de méthane entérique : 1ers résultats
institutdelelevage
PRO
0
120
OWASP AISVS - C7
shiell
2
860
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
970
全国町字単位空き家率推定データver1.0データ仕様
microbaseinc
0
330
AI創薬の壁
kanojikajino
1
1.2k
Featured
See All Featured
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
230
23k
Utilizing Notion as your number one productivity tool
mfonobong
4
640
Why Mistakes Are the Best Teachers: Turning Failure into a Pathway for Growth
auna
0
350
Understanding Cognitive Biases in Performance Measurement
bluesmoon
32
3.1k
Winning Ecommerce Organic Search in an AI Era - #searchnstuff2025
aleyda
2
2.2k
Building Adaptive Systems
keathley
44
3.3k
Typedesign – Prime Four
hannesfritz
42
3.2k
Paper Plane
katiecoart
PRO
5
55k
Balancing Empowerment & Direction
lara
6
1.4k
Making Projects Easy
brettharned
120
6.8k
GraphQLの誤解/rethinking-graphql
sonatard
75
12k
Music & Morning Musume
bryan
48
7.5k
Transcript
A Document Descriptor using Covariance of Word Vectors 文献紹介 2019/02/27
長岡技術科学大学 自然言語処理研究室 稲岡 夢人
Literature 2 Title A Document Descriptor using Covariance of Word
Vectors Author Marwan Torki Volume Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 527-532, 2018.
Abstract 単語ベクトルを用いた固定長の文書表現を提案 (Document-Covariance Descriptor; DoCoV) → Supervised, Unsupervisedのアプリケーションで 簡単に利用できる
様々なタスクでSoTAに匹敵する性能 3
Introduction ベクトルを利用した文書検索には長い歴史がある ← Bag-of-Words, Latent Semantic Indexing(LSI) 近年はニューラル言語モデルで単語埋め込みを学習
単語ではなく文, 段落, 文書の分散表現も注目されている 4
vs. DoCoV doc2vecやFastSentは 単語と共通の空間 共分散は単語の密度の 形状を符号化 5
vs. DoCoV doc2vecやFastSentは学習に時間がかかる DoCoV(共分散)の計算は並列性が高く高速に行える 6
DoCoV Document Observation Matrix d次元の単語埋め込みとn単語の文書において ∈ ×と定義 (行は単語、列は埋め込みの各次元) 7
DoCoV Covariance Matrix 8
DoCoV Vectorized representation 9
Evaluation IMDB movie reviewsの分類性能によって 単語ベクトルによる変化を評価 ベクトルを線形SVMで分類 1つのレビューは複数の文で構成される
Train/Test/Unlabeled : 25K/25K/50K 事前学習済みのword2vec, GloVeと、 TrainとUnlabeledで学習したword2vecで比較 10
Result 11
Result 12
Result 13
Result 14
Evaluation 文の意味関連性データセットSICK, STS 2014で 文書ベクトルを評価 事前学習済みの単語埋め込みを使用 (dim=300)
Pearson correlationとSpearman correlationで評価 15
Result 学習が必要な他手法と匹敵するような結果 16
Evaluation Google newsで事前学習済みの単語埋め込みを使用 Movie Reviews(MR), Subjectivity(Subj), Customer Reviews(CR),
TREC Question(TREC)を データセットとして使用 17
Result 18
Result 19
Result 20
Result 21
Conclusions 文、段落、文書の新たなベクトル表現方法を提案 他手法のような反復の学習を必要としない Supervised, Unsupervisedのタスクにおいて その有用性を確認 22