Upgrade to Pro — share decks privately, control downloads, hide ads and more …
Sign up for free

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

Avatar for onizuka laboratory onizuka laboratory
July 11, 2018
Research
400
0

[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

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
94
Card-660: A Reliable Evaluation Framework for Rare Word Representation Models
Avatar for onizuka laboratory onilab
0
44
A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification
Avatar for onizuka laboratory onilab
0
160
Integrating Transformer and Paraphrase Rules for Sentence Simplification
Avatar for onizuka laboratory onilab
0
70
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
Avatar for onizuka laboratory onilab
0
68
Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
Avatar for onizuka laboratory onilab
0
110
Modeling Multi-turn Conversation with Deep Utterance Aggregation
Avatar for onizuka laboratory onilab
0
100
Learning Semantic Sentence Embeddings using Pair-wise Discriminator
Avatar for onizuka laboratory onilab
0
130

Other Decks in Research

See All in Research
JPA2026_NetworkTutorial_JunKashihara
Avatar for JunKashihara junkashihara
0
140
[最先端NLP勉強会2026] Agentic Rubrics as Contextual Verifiers for SWE Agents
Avatar for Ryo Fujii rfujii
1
350
高性能計算機クラスタを用いた大規模点群処理による森林の単木抽出と構造解析
Avatar for Kenta Itakura kentaitakura
1
120
Cross-Media Human-Information Interaction
Avatar for Beat Signer signer
PRO
0
230
SoftMatcha 2: 1兆語規模コーパスの超高速かつ柔らかい検索
Avatar for Masataka YONEDA e869120_sub
7
3.8k
MIRU2026 チュートリアル講演2：三次元データ処理の動向
Avatar for Naoya Chiba nnchiba
6
4.8k
typst の使い方：言語学を研究する学生のために
Avatar for Tomoya gitomochang
0
580
マーケットストリート 社会実験2024 in 秋葉原ジャンク通り 調査報告書
Avatar for 日本大学 都市計画研究室（泉山ゼミ） izumiyama_lab
1
140
コーディングエージェントとABNを再考
Avatar for Hironobu Fujiyoshi hf149
2
860
Vector Map as Language: Toward Unified Remote Sensing Vector Mapping
Avatar for SatAI.challenge satai
3
270
LINEヤフー データサイエンス Meetup「三井物産コモディティ予測チャレンジ」の舞台裏-AlpacaTechパート
Avatar for tomo gamella
1
660
IA for theory
Avatar for Gabriel Peyré gpeyre
1
410

Featured

See All Featured
Deep Space Network (abreviated)
Avatar for Tony Rice tonyrice
0
300
Neural Spatial Audio Processing for Sound Field Analysis and Control
Avatar for NII S. Koyama's Lab skoyamalab
0
480
Bridging the Design Gap: How Collaborative Modelling removes blockers to flow between stakeholders and teams @FastFlow conf
Avatar for Kenny Baas-Schwegler baasie
0
690
A Modern Web Designer's Workflow
Avatar for Chris Coyier chriscoyier
698
190k
Distributed Sagas: A Protocol for Coordinating Microservices
Avatar for Caitie McCaffrey caitiem20
333
23k
The untapped power of vector embeddings
Avatar for Frank van Dijk frankvandijk
2
1.9k
Side Projects
Avatar for Sacha Greif sachag
455
43k
svc-hook: hooking system calls on ARM64 by binary rewriting
Avatar for Akira Moroo retrage
2
560
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
Avatar for Stéphanie Walter stephaniewalter
287
14k
Docker and Python
Avatar for Tania Allard trallard
47
4.2k
The Pragmatic Product Professional
Avatar for Laura Van Doore lauravandoore
37
7.4k
Max Prin - Stacking Signals: How International SEO Comes Together (And Falls Apart)
Avatar for Tech SEO Connect techseoconnect
PRO
0
450

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