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
文献紹介: Query and Output: Generating Words by Que...
Search
Yumeto Inaoka
July 20, 2018
Research
210
1
Share
文献紹介: Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation
2018/07/20の文献紹介で発表
Yumeto Inaoka
July 20, 2018
More Decks by Yumeto Inaoka
See All by Yumeto Inaoka
文献紹介: Quantity doesn’t buy quality syntax with neural language models
yumeto
1
210
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
280
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
190
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
210
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
200
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
320
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
410
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
250
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
270
Other Decks in Research
See All in Research
IEEE AIxVR 2026 Keynote Talk: "Beyond Visibility: Understanding Scenes and Humans under Challenging Conditions with Diverse Sensing"
miso2024
0
190
東京大学工学部計数工学科、計数工学特別講義の説明資料
kikuzo
0
460
Model Discovery and Graph Simulation: A Lightweight Gateway to Chaos Engineering
anatolykr
0
190
社内データ分析AIエージェントを できるだけ使いやすくする工夫
fufufukakaka
1
1.1k
NII S. Koyama's Lab Research Overview AY2026
skoyamalab
0
270
Harness Engineering and Al Agent
kzinmr
3
1.6k
オーストリア流 都市の公共交通サービス水準評価@公共交通オープンデータ最前線2026
trafficbrain
0
180
AY 2026 Guide to Academic Writing Using Generative AI - Workshop
ks91
PRO
0
110
National high-resolution cropland classification of Japan with agricultural census information and multi-temporal multi-modality datasets
satai
3
260
FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensing
satai
3
840
業界横断 副業コンプライアンス調査 三者(副業者・本業先・発注者)におけるトラブル認知ギャップの構造分析
fkske
0
1.3k
「車1割削減、渋滞半減、公共交通2倍」を 熊本から岡山へ@RACDA設立30周年記念都市交通フォーラム2026
trafficbrain
1
1.1k
Featured
See All Featured
Tell your own story through comics
letsgokoyo
1
940
Lightning talk: Run Django tests with GitHub Actions
sabderemane
0
190
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
49
10k
So, you think you're a good person
axbom
PRO
2
2k
The Cost Of JavaScript in 2023
addyosmani
55
10k
Visual Storytelling: How to be a Superhuman Communicator
reverentgeek
2
550
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
34
2.8k
Bootstrapping a Software Product
garrettdimon
PRO
307
120k
Design of three-dimensional binary manipulators for pick-and-place task avoiding obstacles (IECON2024)
konakalab
0
440
Introduction to Domain-Driven Design and Collaborative software design
baasie
1
820
Winning Ecommerce Organic Search in an AI Era - #searchnstuff2025
aleyda
1
2k
AI Search: Implications for SEO and How to Move Forward - #ShenzhenSEOConference
aleyda
1
1.3k
Transcript
Query and Output: Generating Words by Querying Distributed Word Representations
for Paraphrase Generation Shuming Ma, Xu Sun, Wei Li, Sujian Li, Wenjie Li, Xuancheng Ren. Proceedings of NAACL-HLT 2018, pages 196-206, 2018. จݙհ Ԭٕज़Պֶେֶࣗવݴޠॲཧݚڀࣨ ҴԬເਓ
"CTUSBDU wطଘͷ4FRTFRϞσϧ͕ੜ͢Δจ จ๏తʹਖ਼͍͕͠ҙຯతʹෆదͳ͜ͱ͕Α͋͘Δ w୯ޠࢄදݱͷݕࡧʹΑͬͯ୯ޠΛੜ͢Δ 8PSE&NCFEEJOH"UUFOUJPO/FUXPSL 8&"/ ΛఏҊ wݴ͍͕͑ॏཁͳςΩετฏқԽͱจཁλεΫͰ TUBUFPGUIFBSUΛୡ
!2
*OUSPEVDUJPO w ैདྷͷ4FRTFRϞσϧ୯ޠͷҙຯͰͳ͘܇࿅ ηοτͷ୯ޠύλʔϯΛ҉ه͢Δ͕͋Δ ˡσίʔμͷग़ྗ͕ҙຯతใΛϞσϦϯά ɹ͍ͯ͠ͳ͍ͨΊ w σίʔμͷग़ྗ͕࣋ͭύϥϝʔλ͕ଟ͍ ӅΕͷ࣍ݩ͕ ޠኮαΠζ͕ສͷ߹
ύϥϝʔλ ສͱͳΔ !3
8&"/ w 8PSE&NCFEEJOH"UUFOUJPO/FUXPSL w 3//ͷग़ྗΛΫΤϦͱͯ͠࠷Ұக͢Δࢄදݱ ͷ୯ޠΛBUUFOUJPOΛ༻ͨ͠ݕࡧʹΑͬͯબ w ୯ޠͷࢄදݱΤϯίʔμɺσίʔμͷೖྗ ʹՃ͑ͯग़ྗͷΫΤϦʹΑͬͯߋ৽͞ΕΔ !4
!5 8&"/
!6 8&"/
!7 8&"/
!8 8&"/
ΫΤϦͱ୯ޠͷηοτ͔ΒείΞΛܭࢉ RUλΠϜεςοϓUͷRVFSZ FJJ൪ͷީิ୯ޠ J ʜ O OޠኮαΠζ είΞ͕࠷େͱͳΔ୯ޠΛબ WBMJEBUJPOTFUTͰͷੑೳΛجʹHFOFSBMΛ༻
!9
5SBJOJOH w ୯ޠͷબʹݕࡧΛ༻͍͍ͯΔ͕ɺҰൠతͳ 4FRTFRͱಉ༷ʹඍՄೳ ˠଛࣦؔಉ͡ͷ͕༻Մೳ w "EBN Ћ Ќ Ќ
ЏF !10
&YQFSJNFOUT 5FYU4JNQMJpDBUJPO w %BUBTFUT 1BSBMMFM8JLJQFEJB4JNQMJpDBUJPO$PSQVT 18,1 USBJOWBMJEUFTU
&OHMJTI8JLJQFEJBBOE4JNQMF&OHMJTI8JLJQFEJB &84&8 L USBJOWBMJEUFTU UFTUTFU".5ͰಘΒΕͨͭͷ3FGFSFODFΛ࣋ͭ !11
&YQFSJNFOUT 5FYU4JNQMJpDBUJPO w &WBMVBUJPO.FUSJDT #-&6 ػց༁ฏқԽͰ͘༻͍ΒΕ͍ͯΔࣗಈධՁख๏ ਓखධՁ ྲྀெੑɺଥੑɺฏқ͞ΛͰධՁ ฏқ͞ग़ྗ͕ೖྗͱൺͯͲΕ͚ͩฏқ͔Λࣔ͢
!12
݁Ռ ࣗಈධՁ !13
݁Ռ ਓखධՁ !14
"OBMZTJT w 8&"/ैདྷͷ4FRTFRͱൺͯύϥϝʔλ͕গͳ͍ !15
"OBMZTJT w /54XW1#.53ඞਢͷཁૉΛ͍͍ܽͯΔ w 4#.54"3*ྲྀெ͕ͩҙຯ͕ҟͳΔ !16
"OBMZTJT !17
"OBMZTJT !18 ˢলུ͕ଟ͘ใ͕ෆ͍ͯ͠Δ
"OBMZTJT !19 ˢTJFNFOTNBSUJO SSC TIVSCBͱ͍ͬͨແؔͷ ɹ୯ޠΛग़ྗ
"OBMZTJT !20 ˣྲྀெ͕ͩҙຯ͕ҟͳΓΑΓཧղ͕͘͠ͳ͍ͬͯΔ
$PODMVTJPO w ΫΤϦʹΑΔ୯ޠࢄදݱͷݕࡧ͔Β୯ޠΛੜ ͢ΔFODPEFSEFDPEFSGSBNFXPSLΛఏҊ w ͭͷӳޠฏқԽσʔληοτʹ͓͍ͯ ϕʔεϥΠϯͱൺֱͯ͠#-&6͕ͦΕͧΕ ͓Αͼ্ͨ͠ w ຊϞσϧTUBUFPGUIFBSUΛୡ͍ͯ͠Δ
!21