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
89
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
270
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
170
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
180
Other Decks in Research
See All in Research
RCEへの近道
kawakatz
1
800
Weekly AI Agents News! 7月号 プロダクト/ニュースのアーカイブ
masatoto
0
150
KDD論文読み会2024: False Positive in A/B Tests
ryotoitoi
0
170
marukotenant01/tenant-20240826
marketing2024
0
510
JMED-LLM: 日本語医療LLM評価データセットの公開
fta98
5
1.1k
Weekly AI Agents News! 9月号 プロダクト/ニュースのアーカイブ
masatoto
1
110
Weekly AI Agents News! 7月号 論文のアーカイブ
masatoto
1
200
機械学習による言語パフォーマンスの評価
langstat
6
660
Y.Morita_20240726_JBUG_Fukuoka#18
ymorita613
0
270
Language is primarily a tool for communication rather than thought
ryou0634
4
710
ヘルプデスクの事例で学ぶAIエージェント
masatoto
14
8.3k
Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve
eumesy
PRO
6
1.1k
Featured
See All Featured
The World Runs on Bad Software
bkeepers
PRO
65
11k
Stop Working from a Prison Cell
hatefulcrawdad
267
20k
Building Your Own Lightsaber
phodgson
102
6k
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
4
280
The MySQL Ecosystem @ GitHub 2015
samlambert
250
12k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
41
2.1k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
504
140k
Building an army of robots
kneath
302
42k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
250
21k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
37
1.8k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
13
1.9k
Rails Girls Zürich Keynote
gr2m
93
13k
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)
• • • • •