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
文献紹介: A Document Descriptor using Covariance of...
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Yumeto Inaoka
February 27, 2019
Research
320
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
220
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
280
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
190
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
210
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
210
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
320
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
420
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
250
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
280
Other Decks in Research
See All in Research
姫路市 -都市OSの「再実装」-
hopin
0
1.7k
AY 2026 Guide to Academic Writing Using Generative AI - Workshop
ks91
PRO
0
120
LOSの検討(λ Kansai 2026 in Winter)
motopu
0
140
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
120
Ankylosing Spondylitis
ankh2054
0
170
Using our influence and power for patient safety
helenbevan
0
360
進学校の生徒にはア行の苗字が多いのか
ozekinote
0
440
FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensing
satai
3
860
Cross-Media Information Spaces and Architectures
signer
PRO
0
300
NLP colloquium: AI Safety Survey
kanekomasahiro
0
550
Any-Optical-Model: A Universal Foundation Model for Optical Remote Sensing
satai
3
830
人間中心の意思決定支援AI
yukinobaba
PRO
5
2.6k
Featured
See All Featured
Test your architecture with Archunit
thirion
1
2.3k
jQuery: Nuts, Bolts and Bling
dougneiner
66
8.5k
Automating Front-end Workflow
addyosmani
1370
210k
Optimising Largest Contentful Paint
csswizardry
37
3.7k
Music & Morning Musume
bryan
47
7.2k
Building AI with AI
inesmontani
PRO
1
1.1k
DevOps and Value Stream Thinking: Enabling flow, efficiency and business value
helenjbeal
1
230
Darren the Foodie - Storyboard
khoart
PRO
3
3.4k
Designing for Performance
lara
611
70k
Become a Pro
speakerdeck
PRO
31
6k
Why Your Marketing Sucks and What You Can Do About It - Sophie Logan
marketingsoph
0
170
How to Grow Your eCommerce with AI & Automation
katarinadahlin
PRO
1
200
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