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
190
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
140
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
190
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
130
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
130
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
110
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
230
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
290
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
190
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
190
Other Decks in Research
See All in Research
LLM時代にLabは何をすべきか聞いて回った1年間
hargon24
1
590
Weekly AI Agents News! 10月号 論文のアーカイブ
masatoto
1
460
Global Evidence Summit (GES) 参加報告
daimoriwaki
0
220
VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding
sansan_randd
1
420
文書画像のデータ化における VLM活用 / Use of VLM in document image data conversion
sansan_randd
2
420
論文読み会 KDD2024 | Relevance meets Diversity: A User-Centric Framework for Knowledge Exploration through Recommendations
cocomoff
0
140
PostgreSQLにおける分散トレーシングの現在 - 第50回PostgreSQLアンカンファレンス
seinoyu
0
190
20241115都市交通決起集会 趣旨説明・熊本事例紹介
trafficbrain
0
870
EBPMにおける生成AI活用について
daimoriwaki
0
250
Leveraging LLMs for Unsupervised Dense Retriever Ranking (SIGIR 2024)
kampersanda
2
280
[輪講] Transformer Layers as Painters
nk35jk
4
580
The Fellowship of Trust in AI
tomzimmermann
0
200
Featured
See All Featured
We Have a Design System, Now What?
morganepeng
51
7.3k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
230
52k
Why You Should Never Use an ORM
jnunemaker
PRO
54
9.1k
Git: the NoSQL Database
bkeepers
PRO
427
64k
What’s in a name? Adding method to the madness
productmarketing
PRO
22
3.2k
Designing on Purpose - Digital PM Summit 2013
jponch
116
7.1k
Building a Modern Day E-commerce SEO Strategy
aleyda
38
7k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
3
360
GraphQLとの向き合い方2022年版
quramy
44
13k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
19
2.3k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
330
21k
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
656
59k
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)
• • • • •