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

Selecting Proper Lexical Paraphrase for Children

自然言語処理研究室
October 04, 2013
Research
0
61

Selecting Proper Lexical Paraphrase for Children

Tomoyuki Kajiwara, Hiroshi Matsumoto and Kazuhide Yamamoto. Selecting Proper Lexical Paraphrase for Children. The 25th Conference on Computational Linguistics and Speech Processing (ROCLING 2013), pp.59-73 (2013.10)

自然言語処理研究室

October 04, 2013
Tweet

More Decks by 自然言語処理研究室

See All by 自然言語処理研究室
データサイエンス14_システム.pdf
jnlp
0
330
データサイエンス13_解析.pdf
jnlp
0
380
データサイエンス12_分類.pdf
jnlp
0
290
データサイエンス11_前処理.pdf
jnlp
0
400
Recurrent neural network based language model
jnlp
0
100
自然言語処理研究室 研究概要(2012年)
jnlp
0
100
自然言語処理研究室 研究概要(2013年)
jnlp
0
69
自然言語処理研究室 研究概要(2014年)
jnlp
0
64
自然言語処理研究室 研究概要(2015年)
jnlp
0
120

Other Decks in Research

See All in Research
第4回ナレッジグラフ勉強会：ISWC2023論文読み会
kg_wakate
1
200
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis / Stable Diffusion 3
shunk031
0
450
Prompt Tuning から Fine Tuning への移行時期推定
icoxfog417
17
6.9k
[arXiv'23] SCOPE-RL: A Python Library for Offline RL and Off-Policy Evaluation
harukakiyohara_
0
100
説明可能AI：代表的手法と最近の動向 
yuyay
1
590
20240209 データを肴に熊本の交通を考える会「車１割削減、渋滞半減、公共交通２倍」をめざし世界に学ぼう
trafficbrain
0
790
Equivalence of Geodesics and Importance Weighting from the Perspective of Information Geometry
mkimura
0
130
クリック率を最大化しない推薦システム
joisino
41
14k
Gmail の「メール送信者のガイドライン」強化から 1 ヵ月、今後予想されるメールセキュリティの変化とは
hirachan
1
240
サウナでのプロジェクションマッピングの可能性の検討 / EC71koizumi
yumulab
0
160
マルチモーダルLLMの応用動向の論文調査
masatoto
7
2.8k
The Theory behind Vector DB
matsui_528
0
1.5k

Featured

See All Featured
How To Stay Up To Date on Web Technology
chriscoyier
782
250k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
30
6k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
240
1.2M
Infographics Made Easy
chrislema
238
18k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
356
22k
The Cost Of JavaScript in 2023
addyosmani
15
3.8k
Build your cross-platform service in a week with App Engine
jlugia
225
17k
Imperfection Machines: The Place of Print at Facebook
scottboms
259
12k
StorybookのUI Testing Handbookを読んだ
zakiyama
12
4.6k
Bash Introduction
62gerente
604
210k
Why Our Code Smells
bkeepers
PRO
331
56k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
154
14k

Transcript

  1. 4FMFDUJOH1SPQFS-FYJDBM 1BSBQISBTFGPS$IJMESFO 5PNPZVLJ,BKJXBSB )JSPTIJ.BUTVNPUP ,B[VIJEF:BNBNPUP /BHBPLB6OJWFSTJUZPG5FDIOPMPHZ

  2. -FYJDBM1BSBQISBTFGPS$IJMESFO &MFNFOUBSZTDIPPM +BQBOFTFEJDUJPOBSZ ʲେ٧ΊɿpOBMTUBHFʳ   5IFMBTUTDFOFPGUIFQMBZ ࣳډͷ࠷ޙͷ৔໘ /FXTQBQFS GPS$IJMESFO

    ࠷ޙͷେҰ൪ #JHNBUDIPGUIFMBTU #BTJD7PDBCVMBSZ UP-FBSO  XPSET /FXTQBQFS GPS"EVMUT େ٧ΊͷେҰ൪ #JHNBUDIPGUIFpOBMTUBHF 5PUBMBOOVBMOVNCFS PGWPDBCVMBSZ  XPSET 4FMFDUFECZUIFTJNJMBSJUZ CFUXFFOUIFIFBEXPSE 

  3. #7-#BTJD7PDBCVMBSZUP-FBSO 7PDBCVMBSZUIBU SFHJTUFSFEJO UIFFMFNFOUBSZ TDIPPMEJDUJPOBSZ 7PDBCVMBSZUIBU SFHJTUFSFEJOUIF HFOFSBMEJDUJPOBSZ 7PDBCVMBSZUIBU FMFNFOUBSZ

    TDIPPMTUVEFOUT DBOVTF TV⒏DJFOU 7PDBCVMBSZPG UIFNJOJNVN OFDFTTBSZGPS BMJWJOH  #BTJD7PDBCVMBSZ  XPSET #BTJD7PDBCVMBSZUP-FBSO  XPSET (FOFSBM7PDBCVMBSZ 1BSBQISBTFUP#7- GSPN(7BOE7-  3FBEJOHBTTJTUBODFGPS FMFNFOUBSZTDIPPMTUVEFOUT 7PDBCVMBSZUP-FBSO  XPSET

  4. 3FMBUFE8PSLT •  1BSBQISBTFPGVUJMJ[JOHBEJDUJPOBSZ –  IFBEXPSEˠ IFBEXPSE •  'VKJUBFUBM  ɺ.JOPBOE5BOBLB

       –  IFBEXPSEˠ XPSEGSPNUIFFOEPG           EFpOJUJPOTUBUFNFOU •  ,BKJFUBM  ɺ.JOPBOE5BOBLB  ɺ ,BKJXBSBBOE:BNBNPUP   z5IF EFpOJUJPO TUBUFNFOUT BSF TJNQMFS UIBO UIF IFBEXPSETz z5IF MBTU TFHNFOU SFQSFTFOUT UIF NFBOJOH PG UIF IFBEXPSEz 

  5. 1SPCMFNPG3FMBUFE8PSLT %FpOJUJPO ʲେ٧Ίʳࣳډͷ࠷ޙͷ৔໘ ʲpOBMTUBHFʳUIFMBTUTDFOFPGUIFQBSUZ  1BSBQISBTF ɹ✕େ٧ΊͷେҰ൪ˠ৔໘ͷେҰ൪ ɹ#JHNBUDIPGUIFpOBMTUBHFˠ#JHNBUDIPGUIFTDFOF ɹ✔େ٧ΊͷେҰ൪ˠ࠷ޙͷେҰ൪ ɹ#JHNBUDIPGUIFpOBMTUBHFˠ#JHNBUDIPGUIFMBTU

     "QQSPQSJBUFUBSHFUXPSETBSFOPUBMXBZT GPVOEBUUIFFOEPGEFpOJUJPOT 

  6. 1SPQPTFE.FUIPE

  7. 1SPQPTFE.FUIPEʢʣ •  "DRVJTJUJPOPGUIF5BSHFU8PSE$BOEJEBUFT ᶃ  %J⒏DVMUXPSEJTFYUSBDUFE ᶄ  &OUSJFTPGUIFEJ⒏DVMUXPSEBSFTFBSDIFE ᶅ  8PSETBSFFYUSBDUFE JGUIFZBSFUIFTBNFQBSUPGTQFFDIBTUIFEJ⒏DVMUXPSE

     ・・・ professor ・・・ 【professor】People of status as professor. 【professor】Status as professor. 【professor】Teach learning and skill. 【professor】University teacher. Japanese Dictionary Original Sentence People Status Professor Learning Skill University Teacher ᶄ ᶃ ᶅ

  8. 1SPQPTFE.FUIPEʢʣ •  4FMFDUJPOPGUIF1SPQFS5BSHFU8PSE ᶆ  4JNQMFXPSETBSFFYUSBDUFE ᶇ  4JNJMBSJUJFTPGNFBOJOHBSFDBMDVMBUFE ᶈ  4JNQMFXPSEXJUIUIFIJHIFTUTJNJMBSJUZJTTFMFDUFE 

    Basic Vocabulary to Learn People Learning　 University Skill Teacher　 People Status Professor Learning Skill University Teacher ：0.17 ：0.11　 ：0.08 ：0.13 ：0.25 ᶆ ᶇ ᶈ

  9. &YQFSJNFOUT

  10. $PNQBSBUJWF.FUIPET •  "DRVJTJUJPOPGUIF5BSHFU8PSE$BOEJEBUFT 0OFXPSEJTFYUSBDUFE 'SPNUIFFOEPGEFpOJUJPOTUBUFNFOUT *GJUJTUIFTBNFQBSUPGTQFFDIBTUIFEJ⒏DVMUXPSE  •  4FMFDUJPOPGUIF1SPQFS5BSHFU8PSE 8FJHIUFEWPUJOHCZGPMMPXJOHNFUIPET

    •  'SFRVFODZ •  $PPDDVSSFODFGSFRVFODZ •  1PJOUXJTF.VUVBM*OGPSNBUJPO •  5SJHSBNGSFRVFODZ •  $PTJOFTJNJMBSJUZCFUXFFOEPDVNFOUWFDUPST 

  11. &YQFSJNFOUBM4FUVQ •  &YQFSJNFOUBMPCKFDUEJ⒏DVMUXPSET –  %POPUBQQFBSJO#7- –  "QQFBSNPSFUIBOUJNFT JOUIF.BJOJDIJ/FXT1BQFSQVCMJTIFEJO –  *ODMVEFQBSBQISBTBCMFTJNQMFXPSET

    JOUIFEFpOJUJPOTUBUFNFOUT  •  %JDUJPOBSZ5ISFF+BQBOFTFEJDUJPOBSZ •  5IFTBVSVT+BQBOFTF8PSE/FU 

  12. 1SPDFEVSF   •  &YQFSJNFOUTPOUIFEJ⒏DVMUXPSET –  %FDJEFXFJHIU •  &YQFSJNFOUTPOUIFEJ⒏DVMUXPSET – 

    8FJHIUFEWPUJOH •  &WBMVBUJPO – 5ISFFFWBMVBUPSBSFKVEHFE – %FDJEFCZNBKPSJUZWPUF – %FpOJUJPOPGlQBSBQISBTBCMFz 5IFTJNQMFXPSEDBOCFSFQMBDFEXJUI EJ⒏DVMUXPSEJOUIFPSJHJOBMTFOUFODF 

  13. 1SPDFEVSF    ・・・ professor ・・・ 【professor】People of status

    as professor. 【professor】Status as professor. 【professor】Teach learning and skill. 【professor】University teacher. Japanese Dictionary Original Sentence People Status Professor Learning Skill University Teacher ᶅ/PVOTBSFFYUSBDUFE Basic Vocabulary to Learn People Learning　 University Skill Teacher　 People Status Professor Learning Skill University Teacher ：0.17 ：0.11　 ：0.08 ：0.13 ：0.25 ᶆ4JNQMFXPSETBSFFYUSBDUFE ᶇ4JNJMBSJUJFTPGNFBOJOHBSFDBMDVMBUFE ᶃ%J⒏DVMUXPSEJTFYUSBDUFE ᶄ&OUSJFTPGUIFQSPGFTTPSBSFTFBSDIFE

  14. 3FTVMU   •  "DRVJTJUJPOPGUIF5BSHFU8PSE$BOEJEBUFT –  .PSFQBSBQISBTBCMFTJNQMFXPSETBSFBDRVJSFE –  0OMZQPJOUTEJ⒎FSFODF 

    .BOZQBSBQISBTBCMFTJNQMFXPSET BQQFBSBUUIFFOEPGEFpOJUJPOTUBUFNFOUT /VNCFSPG QBSBQISBTBCMFXPSET 1FSDFOUBHFPG QBSBQISBTBCMFXPSET 1SPQPTFE   $PNQBSBUJWF   

  15. 3FTVMU         

       $PTJOFTJNJMBSJUZ  5SJHSBNGSFRVFODZ  1PJOUXJTF.VUVBM*OGPSNBUJPO  $PPDDVSSFODF'SFRVFODZ  'SFRVFODZ ʲ1SPQPTFEʳ8PSE/FUTJNJMBSJUZ ʲ#BTFMJOFʳ3BOEPNOFTT "DRVJTJUJPOCZDPNQBSBUJWFNFUIPE "DRVJTJUJPOCZQSPQPTFENFUIPE

  16. 3FTVMU         

      % 8FJHIUFEWPUJOHBEETUIF 8PSE/FUTJNJMBSJUZUPUIF#  $ 8FJHIUMFTTWPUJOHBEETUIF 8PSE/FUTJNJMBSJUZUPUIF"  # 8FJHIUFEWPUJOHCZDPNQBSBUJWF NFUIPET     " 8FJHIUMFTTWPUJOHCZDPNQBSBUJWF NFUIPET     ʲ1SPQPTFEʳ8PSE/FUTJNJMBSJUZ ʲ#BTFMJOFʳ3BOEPNOFTT "DRVJTJUJPOCZDPNQBSBUJWFNFUIPE "DRVJTJUJPOCZQSPQPTFENFUIPE

  17. 5IFNFUIPEVUJMJ[JOHGSFRVFODZPSDPOUFYU JOGPSNBUJPOTFMFDUFEQBSBQISBTBCMFXPSE &SSPOFPVT&YBNQMFT   •  5XPPSNPSFTJNQMFXPSETIBWFUIFIJHIFTUTJNJMBSJUZ  &YBNQMF • 

    0SJHJOBM"TVNNBSZPGUIFNBJOQPJOUT •  %FpOJUJPOʲ1PJOUTʳFTTFOUJBM TDPSF HBNF TQPU FTTFOUJBM TDPSF HBNF TQPU  TJNJMBSJUZ TJNJMBSJUZ TJNJMBSJUZ TJNJMBSJUZ

  18. •  5IFOPOQBSBQISBTBCMFXPSEIBWFUIFIJHIFTUTJNJMBSJUZ  &YBNQMF •  0SJHJOBM*DBOQMBZUIFQSPHSBNEVSJOHSFDPSEJOH •  %FpOJUJPOʲ1MBZʳ6TFUIFHBSCBHFBHBJO8IBU XBTHPOFPODFBHBJOSFHBJOTQPXFSBOEMJGF &SSPOFPVT&YBNQMFT

       VTFQBSBQISBTBCMF TJNJMBSJUZ QPXFSOPOQBSBQISBTBCMF TJNJMBSJUZ 5IFNFUIPEVUJMJ[JOHGSFRVFODZPSDPOUFYU JOGPSNBUJPOTFMFDUFEQBSBQISBTBCMFXPSE

  19. $PODMVTJPO 8FQBSBQISBTFEJ⒏DVMUXPSEUPTJNQMFXPSEXJUIUIF IJHIFTUTJNJMBSJUZVTJOHUIFXIPMFEFpOJUJPOTUBUFNFOUT  •  "DRVJTJUJPOPGUIF5BSHFU8PSE$BOEJEBUFT –  .PSFQBSBQISBTBCMFTJNQMFXPSETBSFBDRVJSFE –  .BOZPGUIFNBQQFBSBUUIFFOEPGEFpOJUJPOT

     •  4FMFDUJPOPGUIF1SPQFS5BSHFU8PSE ɹ5IFTFMFDUJPOCBTFEPOUIFTJNJMBSJUZJTCFUUFSUIBO ɹUIFTFMFDUJPOCZGSFRVFODZPSDPOUFYUJOGPSNBUJPO