Upgrade to Pro — share decks privately, control downloads, hide ads and more …

[論紹介] Fast Lexically Constrained Decoding with ...

Avatar for onizuka laboratory onizuka laboratory
July 11, 2018
Research
0
380

[論紹介] Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation

弊研究室で行なったNAACL読み会の発表資料です。

Avatar for onizuka laboratory

onizuka laboratory

July 11, 2018
Tweet

More Decks by onizuka laboratory

See All by onizuka laboratory
Phrase-Based & Neural Unsupervised Machine Translation
Avatar for onizuka laboratory onilab
0
120
Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions
Avatar for onizuka laboratory onilab
0
72
Card-660: A Reliable Evaluation Framework for Rare Word Representation Models
Avatar for onizuka laboratory onilab
0
37
A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification
Avatar for onizuka laboratory onilab
0
130
Integrating Transformer and Paraphrase Rules for Sentence Simplification
Avatar for onizuka laboratory onilab
0
61
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
Avatar for onizuka laboratory onilab
0
57
Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
Avatar for onizuka laboratory onilab
0
100
Modeling Multi-turn Conversation with Deep Utterance Aggregation
Avatar for onizuka laboratory onilab
0
98
Learning Semantic Sentence Embeddings using Pair-wise Discriminator
Avatar for onizuka laboratory onilab
0
120

Other Decks in Research

See All in Research
生成AI による論文執筆サポート・ワークショップ ─ サーベイ／リサーチクエスチョン編 / Workshop on AI-Assisted Paper Writing Support: Survey/Research Question Edition
Avatar for Kenji Saito ks91
PRO
0
140
視覚から身体性を持つAIへ: 巧緻な動作の3次元理解
Avatar for Take Ohkawa tkhkaeio
0
190
Ankylosing Spondylitis
Avatar for Charles Holtzkampf ankh2054
0
110
Multi-Agent Large Language Models for Code Intelligence: Opportunities, Challenges, and Research Directions
Avatar for Fatemeh Fard (UBC) fatemeh_fard
0
120
[Devfest Incheon 2025] 모두를 위한 친절한 언어모델(LLM) 학습 가이드
Avatar for Beomi beomi
2
1.4k
データサイエンティストの業務変化
Avatar for The Japan DataScientist Society datascientistsociety
PRO
0
220
Agentic AI フレームワーク戦略白書 (2025年度版）
Avatar for MIKIO KUBO mickey_kubo
1
120
20251023_くまもと21の会例会_「車1割削減、渋滞半減、公共交通2倍」をめざして.pdf
Avatar for Traffic Brain trafficbrain
0
180
第二言語習得研究における 明示的・暗示的知識の再検討：この分類は何に役に立つか，何に役に立たないか
Avatar for Yu Tamura tam07pb915
0
1.2k
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
Avatar for Yusuke Fukasawa fufufukakaka
1
900
A History of Approximate Nearest Neighbor Search from an Applications Perspective
Avatar for Yusuke Matsui matsui_528
1
160
ウェブ・ソーシャルメディア論文読み会 第36回: The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents (EMNLP, 2025)
Avatar for taichi_murayama hkefka385
0
160

Featured

See All Featured
世界の人気アプリ100個を分析して見えたペイウォール設計の心得
Avatar for Akihiro Kokubo akihiro_kokubo
PRO
66
37k
First, design no harm
Avatar for Per Axbom axbom
PRO
2
1.1k
Designing for Performance
Avatar for Lara Hogan lara
610
70k
Lightning Talk: Beautiful Slides for Beginners
Avatar for Ines Montani inesmontani
PRO
1
440
Neural Spatial Audio Processing for Sound Field Analysis and Control
Avatar for NII S. Koyama's Lab skoyamalab
0
170
XXLCSS - How to scale CSS and keep your sanity
Avatar for Zaharenia Atzitzikaki sugarenia
249
1.3M
Fashionably flexible responsive web design (full day workshop)
Avatar for Andy Clarke malarkey
408
66k
Navigating Weather and Climate Data
Avatar for Ryan Abernathey rabernat
0
110
Building Experiences: Design Systems, User Experience, and Full Site Editing
Avatar for Michelle Schulp Hunt marktimemedia
0
410
Unlocking the hidden potential of vector embeddings in international SEO
Avatar for Frank van Dijk frankvandijk
0
170
A better future with KSS
Avatar for Kyle Neath kneath
240
18k
Ethics towards AI in product and experience design
Avatar for Skipper Chong Warson skipperchong
2
200

Transcript

  1. 'BTU-FYJDBMMZ$POTUSBJOFE%FDPEJOH XJUI%ZOBNJD#FBN"MMPDBUJPO GPS/FVSBM.BDIJOF5SBOTMBUJPO .BUU1PTUBOE%BWJE7JMBS "NB[PO3FTFBSDI #FSMJO (FSNBOZ 1SPDPG/""$- QQ 1SFTFOUFECZ5PNPZVLJ,BKJXBSB

  2. $POUSPMMJOH/.5PVUQVU • /.5SFNPWFTNBOZXBZTPGNBOVBMMZHVJEJOH UIFUSBOTMBUJPOQSPDFTTJOPMEFSQBSBEJHNT 1#4.5  • *ODPSQPSBUFEPNBJOTQFDJGJDEJDUJPOBSJFT • 'PSDFBUSBOTMBUJPODIPJDFGPSDFSUBJOXPSET

    • -FYJDBMMZ$POTUSBJOFE%FDPEJOHGPS4FRVFODF(FOFSBUJPO 6TJOH(SJE#FBN4FBSDI )PLBNQ BOE-JV "$- • 6TFSTDBOTQFDJGZUIFXPSETUIBUNVTUBQQFBSJOUIFPVUQVU • 6TFGVMGPSUBTLTTVDIBTQPTUFEJUJOH DBQUJPOHFOFSBUJPO   /JFNBOE IBUEJF"CTJDIU FJOF .BVFS[V CBVFO /JFNBOE IBUEJF"CTJDIU FJOF .BVFS[V FSSJDIUFO ,FJOFS IBUEJF"CTJDIU FJOF .BVFS[V CBVFO FSSJDIUFO LFJOFS -FYJDBMMZ$POTUSBJOFE%FDPEJOH /PPOFIBTUIFJOUFOUJPO PGCVJMEJOHBXBMM

  3. (#4IBTBMBSHF3VOUJNF$PNQMFYJUZ %FDPEJOH$PNQMFYJUZ 0 /L$ (SJE#FBN4FBSDI )PLBNQ BOE-JV  0 /L

    %ZOBNJD#FBN"MMPDBUJPO 5IJT8PSL /TFOUFODFMFOHUI LCFBNTJ[F $OVNCFSPGDPOTUSBJOUT (#4IBTUXPQSPCMFNT • %FDPEJOHDPNQMFYJUZJTMJOFBSJODPOTUSBJOUT • $BOOPUTQFDJGZUIFCFBNTJ[FBUNPEFMMPBEUJNF 

  4. %#"%ZOBNJD#FBN"MMPDBUJPO • 4JNQMZSFQMBDFUIF,#&45 JNQMFNFOUBUJPO GSPNUIFBMHPSJUINPGTUBOEBSECFBNEFDPEJOH • *OTUFBEPGTFMFDUJOHUIFUPQLJUFNT  (FOFSBUJOHBMJTUPGDBOEJEBUFT 8FOPXOFFEUPFOTVSFUIBUDBOEJEBUFTQSPHSFTT

    UISPVHIUIFTFUPGQSPWJEFEDPOTUSBJOUT  "MMPDBUJOHUIFCFBNBDSPTTUIFDPOTUSBJOUCBOLT 8JUIBGJYFETJ[FECFBNBOEBSCJUSBSZOVNCFSPG DPOTUSBJOUT XFOFFEUPGJOEBOBMMPDBUJPOTUSBUFHZ  GVODUJPO #&".4&"3$) / L CFBNˡ %&$0%&3*/*5 L GPS UJNFTUFQUJO/EP TDPSFT%&$0%&345&1 CFBN CFBNˡ ,#&45 TDPSFT SFUVSO CFBN<>

  5. 4UFQ(FOFSBUJOHUIFDBOEJEBUFTFU $BOEJEBUFTFU ˒ LCFTUJUFNT JF OPSNBMUPQL ˖ TJOHMFCFTUUPLFO ˠ VOGJMMFEDPOTUSBJOUT

     #FBNTJ[F L  7PDBCVMBSZTJ[F c7c  $POTUSBJOUT $  XPSET QISBTF

  6. 4UFQ"MMPDBUJOHUIFCFBN "MMPDBUFTJ[FLCFBNBDSPTT$ DPOTUSBJOUCBOLT #BOL 5IFQPSUJPOPGUIFCFBNSFTFSWFEGPSJUFNT IBWJOHNFUUIFTBNFOVNCFSPGDPOTUSBJOUT "MMPDBUJPOTUSBUFHZTFUUJOHFBDICJOTJ[FUP⌊L$⌋ "OZSFNBJOJOHTMPUTBSFBTTJHOFEUPUIFNPTUDPOTUSBJOFECBOL 

  7. &YQFSJNFOUBM4FUVQ • %BUB • 5SBJO8.5&OHMJTI(FSNBOUSBJOJOHDPSQPSB • %FW5FTUOFXTUFTU  • 1SFQSPDFTT

    • .PTFTUPLFOJ[FS • +PJOU#1&WPDBCVMBSZXJUILNFSHFPQFSBUJPO • .PEFM • MBZFS3//XJUIBUUFOUJPO • "EBNPQUJNJ[FSXJUIBCBUDITJ[FPG • &BSMZTUPQQJOH DSPTTFOUSPQZ • #BTFMJOFT • (SJE#FBN4FBSDI LC $  C   

  8. 3VOOJOHUJNF MPXFSJTCFUUFS BOE#-&6TDPSF • 5IFMJOFBSUSFOEJO$ DPOTUSBJOUT JTDMFBSGPS(#4 • 5IFDPOTUBOUUSFOEJO$ JTDMFBSGPS%#"

    • %#"JTBCPVUYTMPXFSUIBOVODPOTUSBJOFEEFDPEJOH  #-&6 #-&6 #-&6

  9. $POTUSBJOFEXPSETBSFQMBDFEJOUIFDPSSFDUQPTJUJPO 1FBSTPO`TS  

  10. $POTUSBJOFEXPSETBSFQMBDFEJOUIFDPSSFDUQPTJUJPO 

  11. .PEFMTDPSFHPFTEPXOCVU#-&6TDPSFHPFTVQ 5IJTJTBOPCTFSWBUJPOSFMBUFEUPBSFQPSU UIBU #-&6XPSTFOTJGUIFCFBNTJ[FJTNBEFUPPMBSHF  ,PFIOBOE,OPXMFT 8/.5 4JY$IBMMFOHFTGPS/FVSBM.BDIJOF5SBOTMBUJPO

  12. 'BTU-FYJDBMMZ$POTUSBJOFE%FDPEJOHXJUI%#"GPS/.5 • 5IJTTUVEZNBEFJUQPTTJCMFUPDPOUSPM/.5PVUQVU VTJOH-FYJDBMMZ$POTUSBJOFE%FDPEJOH • *O(#4 UIFDPNQVUBUJPOBMDPTUJODSFBTFEMJOFBSMZ XJUI DPOTUSBJOUT CVUJO%#"

    JUEFDSFBTFEUPDPOTUBOU PSEFS • $POTUSBJOUTBSFDPSSFDUMZQMBDFEXPBMJHONFOUJOGPSNBUJPO