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
180
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
120
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
160
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
120
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
120
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
87
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
210
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
260
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
160
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
170
Other Decks in Research
See All in Research
-SSII技術マップを通して見る過去・現在,そして未来-
hf149
1
490
[Human-AI Decision Making勉強会] 説明の更新はユーザにどのような影響をもたらすか
okoso
1
310
ソースコード問い合わせのための長コンテキストLLM向けRAG手法の提案
toskamiya
0
140
AIを前提とした体験の実現に向けて/toward_ai_based_experiences
monochromegane
1
430
IVILab. Research Introduction
ysugano
0
260
スモールデータ勉強会発表資料
natsutan
0
310
ICLR2024 LLMエージェントの研究動向
masatoto
13
9.1k
SSII2024 [OS3] 基盤モデル(オープニング)
ssii
PRO
0
280
機械学習と数理最適化の融合-文脈付き確率的最短路を例として-
mickey_kubo
2
670
Weekly AI Agents News!
masatoto
18
11k
SSII2024 [PD] 画像センシングの未来
ssii
PRO
0
290
Evolutionary Optimization ofModel Merging Recipes (2024/04/17, NLPコロキウム)
iwiwi
9
5k
Featured
See All Featured
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
13
430
Fantastic passwords and where to find them - at NoRuKo
philnash
42
2.7k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
34
1.9k
Adopting Sorbet at Scale
ufuk
71
8.8k
The Cost Of JavaScript in 2023
addyosmani
31
4.7k
Building a Scalable Design System with Sketch
lauravandoore
458
32k
Infographics Made Easy
chrislema
238
18k
A Tale of Four Properties
chriscoyier
155
22k
Put a Button on it: Removing Barriers to Going Fast.
kastner
58
3.3k
Making Projects Easy
brettharned
111
5.7k
Designing the Hi-DPI Web
ddemaree
276
34k
Embracing the Ebb and Flow
colly
81
4.3k
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)
• • • • •