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
38
A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification
onilab
0
140
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
81
Other Decks in Research
See All in Research
製造業主導型経済からサービス経済化における中間層形成メカニズムのパラダイムシフト
yamotty
0
510
LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection
satai
3
610
20年前に50代だった人たちの今
hysmrk
0
170
その推薦システムの評価指標、ユーザーの感覚とズレてるかも
kuri8ive
1
340
YOLO26_ Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection
satai
3
120
LLM-jp-3 and beyond: Training Large Language Models
odashi
1
780
AI Agentの精度改善に見るML開発との共通点 / commonalities in accuracy improvements in agentic era
shimacos
6
1.4k
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
190
Φ-Sat-2のAutoEncoderによる情報圧縮系論文
satai
3
130
svc-hook: hooking system calls on ARM64 by binary rewriting
retrage
2
170
LiDARセキュリティ最前線(2025年)
kentaroy47
0
270
Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities
satai
3
640
Featured
See All Featured
Build The Right Thing And Hit Your Dates
maggiecrowley
39
3.1k
Marketing Yourself as an Engineer | Alaka | Gurzu
gurzu
0
150
Navigating Weather and Climate Data
rabernat
0
140
Odyssey Design
rkendrick25
PRO
2
540
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
inesmontani
PRO
3
2.1k
Making Projects Easy
brettharned
120
6.6k
Designing Experiences People Love
moore
143
24k
The #1 spot is gone: here's how to win anyway
tamaranovitovic
2
990
WCS-LA-2024
lcolladotor
0
480
Automating Front-end Workflow
addyosmani
1370
200k
Primal Persuasion: How to Engage the Brain for Learning That Lasts
tmiket
0
290
Believing is Seeing
oripsolob
1
83
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