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
Personalizing Lexical Simplification
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
onizuka laboratory
October 17, 2018
Research
0
79
Personalizing Lexical Simplification
弊研究室で行なったCOLING2018読み会の発表資料です。
onizuka laboratory
October 17, 2018
Tweet
Share
More Decks by onizuka laboratory
See All by onizuka laboratory
Phrase-Based & Neural Unsupervised Machine Translation
onilab
0
120
Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions
onilab
0
72
Card-660: A Reliable Evaluation Framework for Rare Word Representation Models
onilab
0
37
A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification
onilab
0
130
Integrating Transformer and Paraphrase Rules for Sentence Simplification
onilab
0
61
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
onilab
0
57
Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
onilab
0
100
Modeling Multi-turn Conversation with Deep Utterance Aggregation
onilab
0
98
Learning Semantic Sentence Embeddings using Pair-wise Discriminator
onilab
0
120
Other Decks in Research
See All in Research
LiDARセキュリティ最前線(2025年)
kentaroy47
0
110
20年前に50代だった人たちの今
hysmrk
0
140
LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection
satai
3
460
LLM-jp-3 and beyond: Training Large Language Models
odashi
1
760
Stealing LUKS Keys via TPM and UUID Spoofing in 10 Minutes - BSides 2025
anykeyshik
0
180
ブレグマン距離最小化に基づくリース表現量推定:バイアス除去学習の統一理論
masakat0
0
130
空間音響処理における物理法則に基づく機械学習
skoyamalab
0
190
Collective Predictive Coding and World Models in LLMs: A System 0/1/2/3 Perspective on Hierarchical Physical AI (IEEE SII 2026 Plenary Talk)
tanichu
1
240
【SIGGRAPH Asia 2025】Lo-Fi Photograph with Lo-Fi Communication
toremolo72
0
110
ローテーション別のサイドアウト戦略 ~なぜあのローテは回らないのか?~
vball_panda
0
280
[IBIS 2025] 深層基盤モデルのための強化学習驚きから理論にもとづく納得へ
akifumi_wachi
19
9.5k
A History of Approximate Nearest Neighbor Search from an Applications Perspective
matsui_528
1
150
Featured
See All Featured
Put a Button on it: Removing Barriers to Going Fast.
kastner
60
4.2k
Efficient Content Optimization with Google Search Console & Apps Script
katarinadahlin
PRO
0
310
Designing for humans not robots
tammielis
254
26k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
508
140k
Navigating Algorithm Shifts & AI Overviews - #SMXNext
aleyda
0
1.1k
Designing for Timeless Needs
cassininazir
0
130
16th Malabo Montpellier Forum Presentation
akademiya2063
PRO
0
47
Redefining SEO in the New Era of Traffic Generation
szymonslowik
1
210
XXLCSS - How to scale CSS and keep your sanity
sugarenia
249
1.3M
Building AI with AI
inesmontani
PRO
1
680
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
PRO
196
71k
Transcript
COLING Personalizing Lexical Simplification 2018/10/17 M1
;' • Lexical SimplificationLS1+50)8% • 1+50&7 6 • /20!-:
LS,* • -:. 9"( • $1 50Target # • $1 50Candidate43 2
• Lexical SimplificationLS • • •
• • • • • 3
4 Complex Sentence The cat perched on the mat. Substitution
Generation perched : rested, sat, alighted Substitution Ranking #1 : sat, #2 : rested Substitution Selection perched : rested, sat Complex Word Identification The cat perched on the mat. Simplification Sentence The cat sat on the mat.
Complex Word IdentificationCWI • SemEval2016 • 1
• 20 ! 0.244 • 5
23$" /40#:5 LS,* Complex Word Identification • 4-1+80/:5 )! •
%9 Target. Substitution RankingSubstitution Selection ? • '7(801+80 • 6& 6
(%$&)94 • 15+!*'% • 12000@=50#"!: 1. / 2. /
3. / 3?8 or 3?D 4. 6. . 5. A2@=3? . Low Proficiency 074+ 218@=;-CE<41% High Proficiency ,74+ 218@=;-CE<75% 7 1-4> 5B@
8 Targetavoid BenchLS
" #-4'* ( • 40+# !)% •
F& • #- +#,#- +#$ 9
3=#4 • nilBaseline • Target 86( 7. • Candidate
86( +: • gold • 27.+:*, • +:Target7.Candidate'; • auto0-"& • 40586</9/! %$ • ! 7.+: 1) 10
)%#+ • Precision • !- & • !-,'"*
• ($,'"* • Accuracy • "*,'. • "* • ($,'"* • Readability • "* ,' !- 11
• • Candidate BenchLS •
• • Candidate • 12
13 Candidate • nil
• auto • gold
14 Candidate • nil • auto
• gold
• #+! • 4'). • 40*%
• , " • -* *%$( • &*% $( 15
• Ranking Selection • "!#%' • &) •
( 34.81%$ • 16