Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
Phrase-Based & Neural Unsupervised Machine Tra...
Search
onizuka laboratory
December 18, 2018
Research
120
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Phrase-Based & Neural Unsupervised Machine Translation
弊研究室で行なったEMNLP2018読み会の発表資料です。
onizuka laboratory
December 18, 2018
More Decks by onizuka laboratory
See All by onizuka laboratory
Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions
onilab
0
94
Card-660: A Reliable Evaluation Framework for Rare Word Representation Models
onilab
0
44
A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification
onilab
0
160
Integrating Transformer and Paraphrase Rules for Sentence Simplification
onilab
0
70
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
onilab
0
68
Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
onilab
0
110
Modeling Multi-turn Conversation with Deep Utterance Aggregation
onilab
0
100
Learning Semantic Sentence Embeddings using Pair-wise Discriminator
onilab
0
130
SGM: Sequence Generation Model for Multi-Label Classification
onilab
0
90
Other Decks in Research
See All in Research
Spatial Active Noise Control Based onSound Field Interpolation Incorporating Physical Constraints
skoyamalab
0
190
2026年 オープンキャンパス 研究室紹介
junkurihara
0
190
Fukui Shibiten 39 - AI Art
butchi
0
190
データサイエンティストの就労意識~2015 → 2026 一般(個人)会員アンケートより
datascientistsociety
PRO
0
770
医療LLMの現在地〜最新研究から社会実装までを考える〜
kento1109
1
1.7k
適応的スパムフィルタのための軽量な類似メッセージカウンタ / jsai2026-adaptive-spam-filter
monochromegane
0
5.4k
Harness Engineering and Al Agent
kzinmr
3
2k
SLAMはどこまで解決されたのか?
tomonom
0
1.3k
GLIM とMegaParticles:正規分布近似の限界とタイトカップリング&パーティクルフィルタの進展 / GLIM and MegaParticles : Progress of the distribution representation in SLAM
koide3
0
820
ハードウェア研究で国際トップ会議を目指す!IROS 2027での論文採択を目指して
ayatokanada
6
3.7k
RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent
satai
3
540
Karkada さんの論文 × 2 の紹介: (1) Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models, (2) Symmetry in language statistics shapes the geometry of model representations
eumesy
PRO
1
710
Featured
See All Featured
Sam Torres - BigQuery for SEOs
techseoconnect
PRO
0
540
GraphQLとの向き合い方2022年版
quramy
50
15k
Exploring the relationship between traditional SERPs and Gen AI search
raygrieselhuber
PRO
2
4.3k
Done Done
chrislema
186
16k
How to train your dragon (web standard)
notwaldorf
97
6.8k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
35
2.6k
We Analyzed 250 Million AI Search Results: Here's What I Found
joshbly
1
1.9k
Practical Orchestrator
shlominoach
191
12k
The #1 spot is gone: here's how to win anyway
tamaranovitovic
3
1.2k
Data-driven link building: lessons from a $708K investment (BrightonSEO talk)
szymonslowik
1
1.3k
jQuery: Nuts, Bolts and Bling
dougneiner
66
8.6k
Building Applications with DynamoDB
mza
96
7.2k
Transcript
- & - 1
- & - 2
n 3 • B U o l i b S
N M LP a - k o a • B U o l cT • B e E B
4
5
6
- 7
1 8 a e aM U B . T -.2
- 3- 1 d M M c DM M M A EB P N
1 B .) -0 9 K aM 2 2 (
T 2 P S ,- )238 2 2 M S UL M s D s M t D t 3 02 . C . C
10 French German Russian Romanian Urdu English ) W 6
46 C 2 1 06 - T + + N 97 7 . 75 6 ( JM ) ) 97 7 06 - 2 1 , 97 7
) 0 0 11 , b N S 0 3
I3 1322 5 e ,(B d B 2 3 B 350 3 0 5 (I M e 0 3 I3 1322 5 e T P U f i a T P g B N a T PE
1 12 - vc g ic g 1 A 5
vc g ic g 5 2544 445 A E5 & 41 M vc g ic g mrp f i f MT it 1 A 5 A 5 A54 3 B5 U it 213 B 1 A 1B N & dvosvb T nu e P z it k m mrp f in t i f a l n h T M 0 S ALBLA BLALB MT 0 ST it
13 blPc N kPi L n B nP blP c
N k + 0 +E +PeIa NE M k + + + n P + .- - - T + + + n + U U S lPo N
14
- 15 • T B • P B P M
B • - - B A B P S - -
. ) 16 A EM Ul di M LEU T
BBgcP 0 N .05 . . ol n BNBE B A emP BN ( - kb a
17
18 • S P rs u o - • S
- B • l rs Nc e • S M T o