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
170
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
340
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
単施設でできる臨床研究の考え方
shuntaros
0
2.7k
snlp2025_prevent_llm_spikes
takase
0
170
集合間Bregmanダイバージェンスと置換不変NNによるその学習
wasyro
0
140
SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images
satai
3
190
国際論文を出そう!ICRA / IROS / RA-L への論文投稿の心構えとノウハウ / RSJ2025 Luncheon Seminar
koide3
6
4.8k
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
190
Minimax and Bayes Optimal Best-arm Identification: Adaptive Experimental Design for Treatment Choice
masakat0
0
170
生成的推薦の人気バイアスの分析:暗記の観点から / JSAI2025
upura
0
260
Type Theory as a Formal Basis of Natural Language Semantics
daikimatsuoka
1
290
Language Models Are Implicitly Continuous
eumesy
PRO
0
240
AI エージェントを活用した研究再現性の自動定量評価 / scisci2025
upura
1
150
能動適応的実験計画
masakat0
2
810
Featured
See All Featured
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
285
14k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
33
2.4k
Reflections from 52 weeks, 52 projects
jeffersonlam
352
21k
Documentation Writing (for coders)
carmenintech
74
5k
Building Better People: How to give real-time feedback that sticks.
wjessup
368
19k
Writing Fast Ruby
sferik
628
62k
RailsConf 2023
tenderlove
30
1.2k
The Power of CSS Pseudo Elements
geoffreycrofte
77
6k
Fireside Chat
paigeccino
39
3.6k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
139
34k
Scaling GitHub
holman
463
140k
Stop Working from a Prison Cell
hatefulcrawdad
271
21k
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)
• • • • •