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
200
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
150
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
200
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
140
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
120
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
240
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
300
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
200
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
190
Other Decks in Research
See All in Research
精度を無視しない推薦多様化の評価指標
kuri8ive
1
360
移動ビッグデータに基づく地理情報の埋め込みベクトル化
tam1110
0
240
Composed image retrieval for remote sensing
satai
3
240
打率7割を実現する、プロダクトディスカバリーの7つの極意(pmconf2024)
geshi0820
0
320
eAI (Engineerable AI) プロジェクトの全体像 / Overview of eAI Project
ishikawafyu
0
380
Zipf 白色化:タイプとトークンの区別がもたらす良質な埋め込み空間と損失関数
eumesy
PRO
8
1.3k
Gemini と Looker で営業DX をドライブする / Driving Sales DX with Gemini and Looker
sansan_randd
0
120
請求書仕分け自動化での物体検知モデル活用 / Utilization of Object Detection Models in Automated Invoice Sorting
sansan_randd
0
110
Leveraging LLMs for Unsupervised Dense Retriever Ranking (SIGIR 2024)
kampersanda
2
310
セミコン地域における総合交通戦略
trafficbrain
0
120
知識強化言語モデルLUKE @ LUKEミートアップ
ikuyamada
0
220
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
230
Featured
See All Featured
YesSQL, Process and Tooling at Scale
rocio
172
14k
Measuring & Analyzing Core Web Vitals
bluesmoon
6
250
Side Projects
sachag
452
42k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
30
4.6k
Bash Introduction
62gerente
611
210k
GitHub's CSS Performance
jonrohan
1030
460k
Mobile First: as difficult as doing things right
swwweet
223
9.4k
Git: the NoSQL Database
bkeepers
PRO
427
65k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
44
7k
Docker and Python
trallard
44
3.3k
Optimizing for Happiness
mojombo
376
70k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
21
2.5k
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)
• • • • •