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: Decomposable Neural Paraphrase Generation
Search
Yumeto Inaoka
July 23, 2019
Research
0
230
文献紹介: Decomposable Neural Paraphrase Generation
2019/07/23の文献紹介で発表
Yumeto Inaoka
July 23, 2019
Tweet
Share
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
190
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
240
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
160
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
180
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
160
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
280
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
350
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
230
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
220
Other Decks in Research
See All in Research
VectorLLM: Human-like Extraction of Structured Building Contours via Multimodal LLMs
satai
4
360
EarthSynth: Generating Informative Earth Observation with Diffusion Models
satai
3
420
AIスパコン「さくらONE」の オブザーバビリティ / Observability for AI Supercomputer SAKURAONE
yuukit
2
510
電通総研の生成AI・エージェントの取り組みエンジニアリング業務向けAI活用事例紹介
isidaitc
1
1.1k
論文紹介:Safety Alignment Should be Made More Than Just a Few Tokens Deep
kazutoshishinoda
0
100
一人称視点映像解析の最先端(MIRU2025 チュートリアル)
takumayagi
6
4k
心理言語学の視点から再考する言語モデルの学習過程
chemical_tree
2
650
世界の人気アプリ100個を分析して見えたペイウォール設計の心得
akihiro_kokubo
PRO
63
32k
Stealing LUKS Keys via TPM and UUID Spoofing in 10 Minutes - BSides 2025
anykeyshik
0
150
論文読み会 SNLP2025 Learning Dynamics of LLM Finetuning. In: ICLR 2025
s_mizuki_nlp
0
290
GPUを利用したStein Particle Filterによる点群6自由度モンテカルロSLAM
takuminakao
0
430
不確実性下における目的と手段の統合的探索に向けた連続腕バンディットの応用 / iot70_gp_rff_mab
monochromegane
2
200
Featured
See All Featured
Principles of Awesome APIs and How to Build Them.
keavy
127
17k
Thoughts on Productivity
jonyablonski
71
4.9k
Rebuilding a faster, lazier Slack
samanthasiow
84
9.2k
Designing for humans not robots
tammielis
254
26k
Fantastic passwords and where to find them - at NoRuKo
philnash
52
3.5k
Statistics for Hackers
jakevdp
799
220k
The World Runs on Bad Software
bkeepers
PRO
72
11k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3.1k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
46
7.7k
Imperfection Machines: The Place of Print at Facebook
scottboms
269
13k
Art, The Web, and Tiny UX
lynnandtonic
303
21k
Done Done
chrislema
185
16k
Transcript
Decomposable Neural Paraphrase Generation
https://arxiv.org/abs/1906.09741
• • • •
• • •
•
• • •
• • •
• •
• • = [1 , … , ] • =
[1 , … , ]
• • • ℎ = BiLSTM( ; ℎ−1 , ℎ+1
) • = LSTM ℎ , −1 ; −1 • = GumbelSoftmax( , )
• • = − encoderz (, ) • 1:−1 ,
= − encoderz , 1:−1
• • 1:−1 , = σ 1:−1 , ( |1:−1
, )
• 0 , 1 • = LSTM 0 ; 1
; −1 ; −1 • 1:−1 , = GumbelSoftmax ,
• • ∗ = 0 ∗ = 1
• • ℒ = σ=1 log 1:−1 , + σ=1
log ∗ + σ=1 log ( ∗ 1:−1 ,
• • •
• •
•
• •
• •
• •
• •
• •
• • From 1(best) to 4(worst)
• • • • •