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
Integrating Transformer and Paraphrase Rules fo...
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
onizuka laboratory
December 18, 2018
Research
0
61
Integrating Transformer and Paraphrase Rules for Sentence Simplification
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
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
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
SGM: Sequence Generation Model for Multi-Label Classification
onilab
0
80
Other Decks in Research
See All in Research
AWSの耐久性のあるRedis互換KVSのMemoryDBについての論文を読んでみた
bootjp
1
460
情報技術の社会実装に向けた応用と課題:ニュースメディアの事例から / appmech-jsce 2025
upura
0
310
Attaques quantiques sur Bitcoin : comment se protéger ?
rlifchitz
0
140
Multi-Agent Large Language Models for Code Intelligence: Opportunities, Challenges, and Research Directions
fatemeh_fard
0
120
Remote sensing × Multi-modal meta survey
satai
4
710
令和最新技術で伝統掲示板を再構築: HonoX で作る型安全なスレッドフロート型掲示板 / かろっく@calloc134 - Hono Conference 2025
calloc134
0
550
SREはサイバネティクスの夢をみるか? / Do SREs Dream of Cybernetics?
yuukit
3
380
それ、チームの改善になってますか?ー「チームとは?」から始めた組織の実験ー
hirakawa51
0
660
LLM-jp-3 and beyond: Training Large Language Models
odashi
1
760
存立危機事態の再検討
jimboken
0
240
病院向け生成AIプロダクト開発の実践と課題
hagino3000
0
530
姫路市 -都市OSの「再実装」-
hopin
0
1.6k
Featured
See All Featured
The Curious Case for Waylosing
cassininazir
0
240
Into the Great Unknown - MozCon
thekraken
40
2.3k
4 Signs Your Business is Dying
shpigford
187
22k
How to make the Groovebox
asonas
2
1.9k
Stewardship and Sustainability of Urban and Community Forests
pwiseman
0
110
Mind Mapping
helmedeiros
PRO
0
89
Visualization
eitanlees
150
17k
Making the Leap to Tech Lead
cromwellryan
135
9.7k
Docker and Python
trallard
47
3.7k
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
signer
PRO
0
3.2k
Measuring & Analyzing Core Web Vitals
bluesmoon
9
760
Understanding Cognitive Biases in Performance Measurement
bluesmoon
32
2.8k
Transcript
% 4BORJBOH ;IBP 3VJ .FOH %BRJOH)F 4BQUPOP "OEJ 1BSNBOUP
#BNCBOH 5SBOTGPSNFSBOE1BSBQISBTF 3VMFTGPS4FOUFODF4JNQMJGJDBUJPO #ݪ େو &./-1ಡΈձʢʣ
֓ཁ l 5SBOTGPSNFSϕʔεͷΞʔΩςΫνϟ l ฏқԽݴ͍͑σʔλϕʔε 4JNQMF11%#Λ ౷߹͢Δͭͷख๏ʢ%."44ͱ %$44ʣΛఏҊ l ౷߹ͷϝϦοτͭ
◦ จฏқԽͷ405"ΑΓ༏ΕΔ ◦ ϞσϧΑΓਖ਼֬ͳฏқԽنଇΛબ͠Α͏ͱ͢Δ l ιʔείʔυެ։ ◦ IUUQTHJUIVCDPN4BORJBOHUFYU@TJNQMJGJDBUJPO
5SBOTGPSNFS l ࠨ͕Τϯίʔμ l ӈ͕σίʔμ l ଛࣦؔ "#$ = −
log , ɺݱࡏͷϞσϧͷ શͯͷύϥϝʔλ
4JNQMF11%#ͷ౷߹ l ฏқԽͷχϡʔϥϧωοτϫʔΫϞσϧͰɺ ग़ݱස͕ߴ͍ฏқԽنଇΛ܇࿅͢Δ ◦ සنଇΛϊΠζͱଊ͑ͯ͠·͏ l /.5Ͱͷॳͷ֎෦ࣝ౷߹ ◦ ֎෦ࣝΛ౷߹͢Δ4.5ฏқԽྑ͍ʢ9VFUBM
ʣ l 4JNQMF11%# ◦ 1BWMJDL FUBM ◦ ສͷنଇ
ఏҊख๏̍ɿ%$44 l %FFQ$SJUJD4FOUFODF4JNQMJGJDBUJPO.PEFM l ଛࣦؔΛमਖ਼ ◦ සنଇͷݟམͱ͠Λආ͚ΔͨΊʹɺ୯ޠͷੜ֬Λ ฏқԽ֬Ͱ࠶ॏΈ͚ l ྫ
◦ ೖྗɿUIFSFDJQJFOU PGUIFLBUF HSFFOBXBZ NFEBM ◦ ग़ྗɿUIFXJOOFS PGUIFLBUF HSFFOBXBZ NFEBM l SFDJQJFOUΛग़͠ʹ͘͘ɺ XJOOFSΛग़͘͢͠ ͳΔΑ͏ଛࣦΛฦ͍ͨ͠
%$44ͷଛࣦؔ l 012# ฏқԽنଇͷॏΈɺ Ϟσϧύϥϝʔλɺ ೖྗจ l 304543 ಛఆͷ୯ޠͷΈʹɺ"#$ =
− log , ޠኮશମʹযΛ͍ͯͯΔ ◦ ͜ΕΒͷଛࣦؔΛަޓʹ࠷খԽ͢ΔΑ͏܇࿅
ఏҊख๏̎ɿ%."44 l %FFQ.FNPSZ"VHNFOUFE4FOUFODF 4JNQMJGJDBUJPO.PEFM l %$44සنଇ͕ແࢹ͞Ε͍͢ʢ͔͠͠ ܇࿅σʔλ͕ݶΒΕΔ߹ɺසنଇॏཁʣ l ֤نଇʹෳͷΩʔόϦϡʔ༻ϝϞϦΛ༻ҙ ◦
ΩʔϕΫτϧɺίϯςΩετϕΫτϧʢΤϯίʔμͷӅΕ ঢ়ଶͱͦͷ࣌ࠁͷσίʔμӅΕঢ়ଶͷՃॏฏۉʣ ◦ όϦϡʔϕΫτϧɺग़ྗϕΫτϧ
%."44
σʔληοτ l ܇࿅ 8JLJ-BSHF ;IBOHBOE-BQBUB ◦ จର l
ݕূͱධՁɺ5VSL 9VFUBM ◦ ೖྗจʹରͯ͠ਓखͷ̔ϦϑΝϨϯεʢˠྑ࣭ʣ ◦ ݕূ༻ จରɺධՁ༻ จର l ධՁ༻ʹ /FXTFMB ͏ ◦ จର
ධՁࢦඪ l ',(-ʢจͷฏқੑʣ ◦ จͷ͞ͱޠ͔Βܭࢉ l 4"3*ʢՃɾআɾอ࣋͞Ε͍ͯΔ͔ʣ ◦ ೖྗɺग़ྗɺϦϑΝϨϯεΛൺֱ l
نଇར༻ੑʢޠኮมͷਖ਼֬ੑʣ ◦ 4"3*ʹՃͱআΛผʑʹධՁ͢Δ͕ɺ߹Θ͍ͤͨ ◦ ೖྗͱϦϑΝϨϯεΛൺֱ͠ɺฏқԽنଇΛௐͯ ͦΕʹର͢Δ QSFDJTJPOɺSFDBMMɺ'Λܭࢉ
5SBOTGPSNFSͷ݁Ռʢ5VSLʣ l ',(-ͱ 4"3*͕ 3//-45.ΑΓ༏Ε͍ͯͨ l -)͕૿Ճ͢ΔͱείΞ্͕ͬͨ
5SBOTGPSNFSͷ݁Ռʢ5VSLʣ l -)͕૿Ճ͢Δͱ ',(-ͷԼ͕Δ l 4"3*ͷอ͚࣋ͩݮগɺաʹฏқԽͯ͠͠·͏
11%#౷߹ͷ݁Ռʢ5VSLʣ
11%#౷߹ͷ݁Ռʢ5VSLʣ
11%#౷߹ͷ݁Ռʢ5VSLʣ
11%#౷߹ͷ݁Ռʢ/FXTFMBʣ