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
250
0
Share
文献紹介: Decomposable Neural Paraphrase Generation
2019/07/23の文献紹介で発表
Yumeto Inaoka
July 23, 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
210
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
270
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
200
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
190
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
390
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
270
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
240
Other Decks in Research
See All in Research
英語教育 “研究” のあり方:学術知とアウトリーチの緊張関係
terasawat
1
930
「AIとWhyを深堀る」をAIと深堀る
iflection
0
350
20年前に50代だった人たちの今
hysmrk
0
190
2026年1月の生成AI領域の重要リリース&トピック解説
kajikent
0
990
【NICOGRAPH2025】Photographic Conviviality: ボディペイント・ワークショップによる 同時的かつ共生的な写真体験
toremolo72
0
230
論文紹介 "ReSim: Reliable World Simulation for Autonomous Driving"
kogo
0
510
Can We Teach Logical Reasoning to LLMs? – An Approach Using Synthetic Corpora (AAAI 2026 bridge keynote)
morishtr
1
220
言語モデルから言語について語る際に押さえておきたいこと
eumesy
PRO
5
2.2k
データサイエンティストの業務変化
datascientistsociety
PRO
0
390
Sequences of Logits Reveal the Low Rank Structure of Language Models
sansantech
PRO
1
230
COFFEE-Japan PROJECT Impact Report(海ノ向こうコーヒー)
ontheslope
0
1.5k
東京大学工学部計数工学科、計数工学特別講義の説明資料
kikuzo
0
360
Featured
See All Featured
The Limits of Empathy - UXLibs8
cassininazir
1
320
Documentation Writing (for coders)
carmenintech
77
5.3k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
10k
Raft: Consensus for Rubyists
vanstee
141
7.4k
brightonSEO & MeasureFest 2025 - Christian Goodrich - Winning strategies for Black Friday CRO & PPC
cargoodrich
3
690
How To Speak Unicorn (iThemes Webinar)
marktimemedia
1
450
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
200
How to Grow Your eCommerce with AI & Automation
katarinadahlin
PRO
1
180
Ethics towards AI in product and experience design
skipperchong
2
270
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
47
8.1k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
35
2.4k
Scaling GitHub
holman
464
140k
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)
• • • • •