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
Generative Models 2025
takahashihiroshi
25
14k
Adaptive Experimental Design for Efficient Average Treatment Effect Estimation and Treatment Choice
masakat0
0
130
論文読み会 SNLP2025 Learning Dynamics of LLM Finetuning. In: ICLR 2025
s_mizuki_nlp
0
290
Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image Classification
satai
3
150
EcoWikiRS: Learning Ecological Representation of Satellite Images from Weak Supervision with Species Observation and Wikipedia
satai
3
300
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
20250605_新交通システム推進議連_熊本都市圏「車1割削減、渋滞半減、公共交通2倍」から考える地方都市交通政策
trafficbrain
0
910
論文紹介:Not All Tokens Are What You Need for Pretraining
kosuken
0
200
Sat2City:3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion
satai
3
180
Combinatorial Search with Generators
kei18
0
1k
PhD Defense 2025: Visual Understanding of Human Hands in Interactions
tkhkaeio
1
270
日本語新聞記事を用いた大規模言語モデルの暗記定量化 / LLMC2025
upura
0
280
Featured
See All Featured
The Language of Interfaces
destraynor
162
25k
Faster Mobile Websites
deanohume
310
31k
[RailsConf 2023] Rails as a piece of cake
palkan
57
5.9k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
34
2.3k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
10
890
Optimizing for Happiness
mojombo
379
70k
The Straight Up "How To Draw Better" Workshop
denniskardys
239
140k
Side Projects
sachag
455
43k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
46
7.7k
Become a Pro
speakerdeck
PRO
29
5.6k
Large-scale JavaScript Application Architecture
addyosmani
514
110k
The World Runs on Bad Software
bkeepers
PRO
72
11k
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)
• • • • •