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
Neural Quality Estimation of Grammatical Error ...
Search
youichiro
January 20, 2019
Technology
0
230
Neural Quality Estimation of Grammatical Error Correction
長岡技術科学大学
自然言語処理研究室
文献紹介(2019-01-22)
youichiro
January 20, 2019
Tweet
Share
More Decks by youichiro
See All by youichiro
日本語文法誤り訂正における誤り傾向を考慮した擬似誤り生成
youichiro
0
1.6k
分類モデルを用いた日本語学習者の格助詞誤り訂正
youichiro
0
100
Multi-Agent Dual Learning
youichiro
1
180
Automated Essay Scoring with Discourse-Aware Neural Models
youichiro
0
120
Context is Key- Grammatical Error Detection with Contextual Word Representations
youichiro
1
140
勉強勉強会
youichiro
0
88
Confusionset-guided Pointer Networks for Chinese Spelling Check
youichiro
0
190
A Neural Grammatical Error Correction System Built On Better Pre-training and Sequential Transfer Learning
youichiro
0
170
An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction
youichiro
0
200
Other Decks in Technology
See All in Technology
私のMCPの使い方
tsubakimoto_s
0
110
AIエージェント入門 〜基礎からMCP・A2Aまで〜
shukob
0
110
All About Sansan – for New Global Engineers
sansan33
PRO
1
1.2k
現場データから見える、開発生産性の変化コード生成AI導入・運用のリアル〜 / Changes in Development Productivity and Operational Challenges Following the Introduction of Code Generation AI
nttcom
0
360
データ戦略部門 紹介資料
sansan33
PRO
1
3.8k
Zephyr(RTOS)にEdge AIを組み込んでみた話
iotengineer22
0
200
CoRL 2025 Survey
harukiabe
1
230
物体検出モデルでシイタケの収穫時期を自動判定してみた。 #devio2025
lamaglama39
0
240
Bill One 開発エンジニア 紹介資料
sansan33
PRO
4
14k
20251014_Pythonを実務で徹底的に使いこなした話
ippei0923
0
220
大規模サーバーレスAPIの堅牢性・信頼性設計 〜AWSのベストプラクティスから始まる現実的制約との向き合い方〜
maimyyym
10
5k
Introduction to Sansan, inc / Sansan Global Development Center, Inc.
sansan33
PRO
0
2.8k
Featured
See All Featured
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
162
15k
Build your cross-platform service in a week with App Engine
jlugia
232
18k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
23
1.5k
Six Lessons from altMBA
skipperchong
29
4k
What’s in a name? Adding method to the madness
productmarketing
PRO
24
3.7k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.5k
Navigating Team Friction
lara
190
15k
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
10
600
Speed Design
sergeychernyshev
32
1.2k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3.1k
Testing 201, or: Great Expectations
jmmastey
45
7.7k
How to Think Like a Performance Engineer
csswizardry
27
2.1k
Transcript
Neural Quality Estimation of Grammatical Error Correction 9 2 0
- 1 Shamil Chollampatt and Hwee Tou Ng EMNLP 2018, pages 2528–2539
• C G E • E - ) (
;. • >A!A!1 <#2< %647- • A!*+08&'
"A!$)= A!,/ *(9 • @B?+08& 35>A!:
- G G C E - - -
( ) • !" , … , !% , &"
, … , &'(" , &')" , … , &* &' M • M P P: ) P : • P: +' )(
2 2 • / 2 2 / 2 M H
• E M E R T
y uo vkhm • F EL GFMG L GF F
L F NG C 1 . EG :.AG E F + hPed i • 1 . G 5 G G Q 2 F + ( • E G G Q 8.2 0. +)C Pclan • -M , hPe c w sW gcihPe c U] • 6L , p t [ T c 7 6 C Pclan TW r
: HCM ) ( E ) P N NQE$% ,
) ) NQE&'' NQE(( NQE)( NQE)) NQE() : : P
: N : ( : C ) E E PM
NQE$% 2 , ) ) NQE&'' NQE(( NQE)( NQE)) NQE() : E
2 2
!* ," ).# (
'&-$%+
• iE M c df 2 - • dfM M
e P M E • dfM h a
+. : m c e_ a j iPhig M fd
l 1. P +. : : : P D 4 . :/1105 3 . . - 11 5 3 02-05 02
) 0 2 ( 11 0 2 01