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
210
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
160
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
210
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
140
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
150
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
130
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
250
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
310
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
210
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
200
Other Decks in Research
See All in Research
JSAI NeurIPS 2024 参加報告会(AI アライメント)
akifumi_wachi
5
920
大規模言語モデルを用いたニュースデータのセンチメント判定モデルの開発および実体経済センチメントインデックスの構成
nomamist
1
150
ベイズ的方法に基づく統計的因果推論の基礎
holyshun
0
920
Satellite Sunroof: High-res Digital Surface Models and Roof Segmentation for Global Solar Mapping
satai
3
190
Vision Language Modelと完全自動運転AIの最新動向
tsubasashi
1
310
Weekly AI Agents News! 2月号 アーカイブ
masatoto
1
110
公立高校入試等に対する受入保留アルゴリズム(DA)導入の提言
shunyanoda
0
310
DeepSeek を利用する上でのリスクと安全性の考え方
schroneko
3
1.2k
サーブレシーブ成功率は勝敗に影響するか?
vball_panda
0
600
リモートワークにおけるパッシブ疲労
matsumoto_r
PRO
6
5k
地理空間情報と自然言語処理:「地球の歩き方旅行記データセット」の高付加価値化を通じて
hiroki13
1
220
A Segment Anything Model based weakly supervised learning method for crop mapping using Sentinel-2 time series images
satai
3
180
Featured
See All Featured
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
29
2.5k
How To Stay Up To Date on Web Technology
chriscoyier
790
250k
jQuery: Nuts, Bolts and Bling
dougneiner
63
7.7k
Six Lessons from altMBA
skipperchong
27
3.7k
Intergalactic Javascript Robots from Outer Space
tanoku
270
27k
Documentation Writing (for coders)
carmenintech
69
4.7k
Building Adaptive Systems
keathley
41
2.5k
Imperfection Machines: The Place of Print at Facebook
scottboms
267
13k
Site-Speed That Sticks
csswizardry
4
450
Fontdeck: Realign not Redesign
paulrobertlloyd
83
5.4k
Building a Modern Day E-commerce SEO Strategy
aleyda
39
7.2k
Unsuck your backbone
ammeep
670
57k
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)
• • • • •