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
170
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
110
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
150
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
110
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
110
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
77
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
200
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
250
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
150
Other Decks in Research
See All in Research
説明可能AI:代表的手法と最近の動向
yuyay
1
510
IRではデータ収集がどのように実施・認識されてきたのか
gmoriki
0
340
機械学習における重要度重み付けとその応用
mkimura
4
1.6k
第14回対話システムシンポジウム EMNLP 2023 参加報告
atsumoto
0
130
クロスモーダル表現学習の研究動向: 音声関連を中心として
ryomasumura
3
500
第12回全日本コンピュータビジョン勉強会:画像の自己教師あり学習における大規模データセット
naok615
0
480
小説執筆における生成AIの利用
niryuu
0
100
ゼロからわかるリザバーコンピューティング
kurotaky
1
230
[2023 CCSE] ZOZOTOWN検索における 研究開発の取り組みについて
tomoyayama
0
120
3D Human Mesh Estimationについていくつかまとめてみた / Survey about 3D Human Mesh Estimation
nttcom
0
140
論文紹介: Generating News-Centric Crossword Puzzles As A Constraint Satisfaction and Optimization Problem
upura
0
140
データで診て考える合志市の渋滞と公共交通 ~めざせ 車1割削減、渋滞半減、公共交通2倍~
trafficbrain
0
440
Featured
See All Featured
Bootstrapping a Software Product
garrettdimon
PRO
302
110k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
39
4.3k
Stop Working from a Prison Cell
hatefulcrawdad
265
19k
VelocityConf: Rendering Performance Case Studies
addyosmani
319
23k
What's in a price? How to price your products and services
michaelherold
236
11k
Git: the NoSQL Database
bkeepers
PRO
421
63k
No one is an island. Learnings from fostering a developers community.
thoeni
14
2k
Keith and Marios Guide to Fast Websites
keithpitt
407
22k
Facilitating Awesome Meetings
lara
39
5.5k
Mobile First: as difficult as doing things right
swwweet
215
8.5k
JazzCon 2018 Closing Keynote - Leadership for the Reluctant Leader
reverentgeek
178
11k
Principles of Awesome APIs and How to Build Them.
keavy
119
16k
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)
• • • • •