Multi-pass Sieve를 이용한 한국어 상호참조해결 반-자동 태깅 도구

Similar documents
<4E505F415AB1DBB7CEB9FABAF1C1EEC7C3B7A35FBEE0B0FC E687770>

제 2 장육상관측소지상종관기상전문의해독과기입,.,. (FM 12) (FM 13). (WMO) FM 12-Ⅸ Ext. SYNOP, FM 13-Ⅸ Ext. SHIP. ZCZC 612 SMKO01 RKSL AAXX

오투중3-2과학정답1

< BEC7BFECC1F62E687770>

1 1. (,, ) ( ) (,,, )., 1 ( ), ( ) ( ) 30, ( ) , + 1%., 1.

슬라이드 제목 없음

A 001~A 036

KAA2005.9/10 Ãâ·Â

2015년 2월 12일 사랑의 동삭교육 제 호 (2월) 년 2월 12일 사랑의 동삭교육 제 호 (2월) 6 겨울이 되면 1-4 박지예 겨울이 되면 난 참 좋아. 겨울이 되면 귀여운 눈사람도 만들고 겨울이 되면 신나는 눈싸움도 하고 겨울이

PowerPoint 프레젠테이션

HWP Document

< FC1F8B9E6B1B3C0B02E687770>


<C1DF3320B0B3B3E4BFCFBCBA20C0AFC7FCC3BCC5A92035C8A328C7D8BCB3292E706466>

<BACFC7D1B3F3BEF7B5BFC7E22D3133B1C733C8A BFEB2E687770>


16중등빨이수학3-2교부(01~23)

수리 영역 가 형 5. 다음 그림과 같이 크기가 같은 정육면체 개가 한 모서리씩을 공유하 면서 각 면이 평행 또는 수직 관계를 유지한 채로 한 평면 위에 놓여있 다. 그림의 세 꼭짓점 A, B, C에 대한 두 벡터 BA 와 BC 가 이루는 각 의 크기를 h라 할 때,

CS322 중간고사.docx

<313120C0AFC0FCC0DA5FBECBB0EDB8AEC1F2C0BB5FC0CCBFEBC7D15FB1E8C0BAC5C25FBCF6C1A42E687770>

Probability Overview Naive Bayes Classifier Director of TEAMLAB Sungchul Choi

ch3.hwp

김경재 안현철 지능정보연구제 17 권제 4 호 2011 년 12 월


Software Requirrment Analysis를 위한 정보 검색 기술의 응용

딥러닝 첫걸음

Orcad Capture 9.x

<BFA1B9F6B8AEC4A1BBF3C7D8BAB8C7E820BEE0B0FC2E687770>

Ver. DS-2012.T3.DWS.STR-1.0 System Test Report for Digital Watch System Test Cases Specification Test Summary Report Project Team 이동아 Latest update on

< 목 차 > < 가입자 유의사항 >... 5 < 주요내용 요약서 >... 6 < 보험용어 해설 >... 8 < 주요 민원사례 > < 약관조항 안내 > 무배당수호천사플러스상해보험 약관 제 1 관 목적 및 용어의 정의 제 1 조

MATLAB and Numerical Analysis

기획-4-ok.indd

고등학교 수학 요약노트 - 확률과 통계

<BAB8C7E8B0A1C0D4BEC8B3BBBCAD28C0CEC3B5B1B3C0B0C3BB292D E687770>

VP3145-P1495.eps

DIY 챗봇 - LangCon

2 : (Seungsoo Lee et al.: Generating a Reflectance Image from a Low-Light Image Using Convolutional Neural Network) (Regular Paper) 24 4, (JBE

(지도6)_(7단원 202~221)

A y y y y y # 2#

PowerPoint 프레젠테이션

슬라이드 1

hwp

사회통계포럼

±è¼ºÃ¶ Ãâ·Â-1

Ⅰ. Introduction 우리들을 둘러싸고 잇는 생활 환경속에는 무수히 많은 색들이 있습니다. 색은 구매의욕이나 기호, 식욕 등의 감각을 좌우하는 것은 물론 나뭇잎의 변색에서 초목의 건강상태를 알며 물질의 판단에 이르기까지 광범위하고도 큰 역할을 하고 있습니다. 하

< C0FCC0CEC3CA2E687770>

저작자표시 - 비영리 - 변경금지 2.0 대한민국 이용자는아래의조건을따르는경우에한하여자유롭게 이저작물을복제, 배포, 전송, 전시, 공연및방송할수있습니다. 다음과같은조건을따라야합니다 : 저작자표시. 귀하는원저작자를표시하여야합니다. 비영리. 귀하는이저작물을영리목적으로이용할

QbD 적용을위한품질심사해설서 ( 예시 )

Page 2 of 6 Here are the rules for conjugating Whether (or not) and If when using a Descriptive Verb. The only difference here from Action Verbs is wh

+ F F P. = = = F = F F = = 0 cm =x cm =(x+)x x=0 =0 cm cm cm x cm = =0(cm) P. 0 x=y= x= cm FF cm 0 x= x= =x(0-x) x= 0 (+)=x x= (+)=y 0 y= x= x= = 0= 0

RNN & NLP Application

融合先验信息到三维重建 组会报 告[2]


<3136C1FD31C8A35FC3D6BCBAC8A3BFDC5F706466BAAFC8AFBFE4C3BB2E687770>

CH2E-P0273.eps

<C3D6C1BE2DBDC4C7B0C0AFC5EBC7D0C8B8C1F D32C8A3292E687770>

Siemens

ÀÎÅͳÝ-°ø°£µµÇüÇØ

121_중등RPM-1상_01해(01~10)ok

Page 2 of 5 아니다 means to not be, and is therefore the opposite of 이다. While English simply turns words like to be or to exist negative by adding not,

2015

04김호걸(39~50)ok

(001~042)개념RPM3-2(정답)

Journal of Educational Innovation Research 2018, Vol. 28, No. 1, pp DOI: * A Study on the Pe

Slide 1

4 CD Construct Special Model VI 2 nd Order Model VI 2 Note: Hands-on 1, 2 RC 1 RLC mass-spring-damper 2 2 ζ ω n (rad/sec) 2 ( ζ < 1), 1 (ζ = 1), ( ) 1

TTA Verified : HomeGateway :, : (NEtwork Testing Team)

07.051~058(345).fm

생들의 역할을 중심으로 요약 될 수 있으며 구체적인 내용은 다음과 같다. 첫째. 교육의 대상 면에서 학습대상이 확대되고 있다. 정보의 양이 폭발적으로 증가하고 사회체제의 변화가 가속화 되면서 학습의 대상은 학생뿐만 아니라 성인 모두에게 확대되고 있으며 평생학습의 시대가

MVVM 패턴의 이해


인켈(국문)pdf.pdf

Chapter 11 Rate of Reaction

슬라이드 1

에너지경제연구 Korean Energy Economic Review Volume 17, Number 2, September 2018 : pp. 1~29 정책 용도별특성을고려한도시가스수요함수의 추정 :, ARDL,,, C4, Q4-1 -

R을 이용한 텍스트 감정분석

hwp

Journal of Educational Innovation Research 2018, Vol. 28, No. 3, pp DOI: NCS : * A Study on

nonpara6.PDF

Gray level 변환 및 Arithmetic 연산을 사용한 영상 개선



Microsoft PowerPoint Relations.pptx

방송공학회논문지 제18권 제2호

파이널생명과학1해설OK

Unknown

Microsoft PowerPoint - 기계공학실험1-1MATLAB_개요2D.pptx

Stage 2 First Phonics

<C7A5C1F620BEE7BDC4>

( )프로본문_ok

백서2011표지

(......).hwp


13 Who am I? R&D, Product Development Manager / Smart Worker Visualization SW SW KAIST Software Engineering Computer Engineering 3

0 000., , , , 0 0.H H H 0.H , , , , , 0.H6 000,.HH 0 00

untitled

< C6AFC1FD28B1C7C7F5C1DF292E687770>

¼º¿øÁø Ãâ·Â-1

Microsoft PowerPoint - 26.pptx

1 1 x + # 0 x - 6 x 0 # x # 2r sin2x- sin x = 4cos x r 3 r 2r 5 r 3r

Transcription:

Siamese Neural Network 박천음 강원대학교 Intelligent Software Lab. Intelligent Software Lab.

Intro. S2Net Siamese Neural Network(S2Net) 입력 text 들을 concept vector 로표현하기위함에기반 즉, similarity 를위해가중치가부여된 vector 로표현 linear projection // metric learning approach Input Output Original term vector (one-hot) Projected concept vector Model parameters (weights) e.g. word embedding Model parameters IIIIIIIIII pppppppp rrrrrr tttttttt vvvvvvvvvvvv, ttttttttt llllllllllll, 각 oooooooooooo vvvvvvvvvvvvvv ssssss. : min llllllll(. ) llllllllll: ssssssssssssss oooo nnnnnn Intelligent Software Lab. 2

Learning concept vector vector z OOOOOOOOOOOO Projected concept vector VV pp : < > ssssss(vv pp, VV qq ) VV qq : < > HHHHHHHHHHHH: ttttt Model parameters IIIIIIIIII: tttt aa 0,0,, aa 0,kk aa 1,0,, aa 1,kk aa dd,0,, aa dd,kk Original term vector (one-hot) <0, 1, 0, 0,.. 0, 1>_(dx1) Intelligent Software Lab. 3

Model design ffffffffffffffffffffff NN: nnnntt jj = dd ii=0 ww iiii xx ii S2Net: ttww cc jj = ttii VV αα iiii tttt(tt ii ) αα iiii AA aaaaaaaaaaaaaaaaaaaa ffffffffffffffff sigmoid (non-linear) ssssssssss ttww (. ) ff = tttttttt vvvvvvvvvvvv tttt, ff = VV, dd 1 rrrrrr vvvvvvvvvvvv AA = αα iiii, αα dd kk iiii AA ( weights) gg = AA TT ff ssssmm AA (ff pp, ff qq ) vvvvvvvvvvvv gg kk 1 ( projected concept vector) Intelligent Software Lab. 4

Loss function using the cosine similarity tttttttt vvvvvvvvvvvv pppppppp ff pp, ff qq cccccccccccccccccccccccccc cccccccccccccc vvvvvvvvvvvvvv cccccccccccc vvvvvvvvvv gg pp, gg qq gg pp = AA TT ff pp, gg qq = AA TT ff qq ssssmm AA ff pp, ff qq = TTTTTTTT llllllllll = yy pppp gg pp gg pp TT gg qq gg qq llllllll ffffffffffffffff(mmmmmm) = 1 2 yy pppp ssssmm AA ff pp, ff qq 2 요런방법도있음 ( 기본적인방법 ) query 에가까운 text object 를선택하기위해 MSE 사용 Intelligent Software Lab. 5

Training procedure : ssssssssssssssssssss ssssssssss tttttttt vvvvvvvvvvvv ff ppp, ff qqq, (ff ppp, ff qqq ) 를비교 첫번째 term vector 가더 high similarity 식으로표현하면 = ssssmm AA ff ppp, ff qqq ssssmm AA ff ppp, ff qqq 를 logistic loss 로변환 [0 or 1] 로 loss 값을반올림 LL ; AA = log(1 + exp γγ ) 값이커질수록 loss 값이작아짐 γγ 는 cosine function 때문에 를 γγ 만큼확대시킴 ( dddddddddddddd : [-2, 2]) 따라서 prediction error 에도움됨 γγ 는경험상크게 (= 10) 여기서 AA 를최적화 ( 타겟, high score) ( 출력 ) 본논문에서의 loss function Intelligent Software Lab. 6

Gradient derivation LL ; AA 에서 AA 최적화 LL ;AA AA = γγ 1+exp( γγ ) AA = ssssmm AA AA AA ff ppp, ff qqq ssssmm AA AA ff pp, ff qq cos gg pp, gg qq = AA ssssmm AA ff pp2, ff qq2 = AA cos gg pp, gg qq gg pp TT gg qq gg pp gg qq 1 AA gg TT pp gg qq = AA AA TT ff pp gg qq + AA AA TT ff qq gg pp = ff pp gg TT TT qq + ff qq gg pp 1 = gg TT 1 2 2 gg pp gg pp pp 1 2 3 = 1 2 gg pp TT gg pp 23 AA gg pp TT gg pp = gg pp TT gg pp 23 ff pp gg pp TT LL ; AA = log(1 + exp γγ ) = ssssmm AA ff ppp, ff qqq gg pp = AA TT ff pp, ssssmm AA ff ppp, ff qqq gg qq = AA TT ff qq 3 1 gg qq = gg qq TT gg qq 2 3 ff qq gg qq TT Intelligent Software Lab. 7

S2Net example: max() Input sentences Sen1: what movies johnny depp is in? Sen2: what movies does johnny depp play in? Sen3: who has been married to julia roberts? Bag of words(size 16): Term vector: Intelligent Software Lab. 8

S2Net example: max() cont` Weights: (size: 2 x 16) 0.005 0.0015 0.1 0.075 0.12 0.005 0.0015 0.02 0.1 0.05 0.1 0.05 0.1 0.05 0.0005 0.2 0.003 0.2 0.1 0.005 0.1 0.08 0 0.075 0 0.09 0.2 0.076 0.005 0.0125 0.065 0.01 xx ii xx ww WW TT Intelligent Software Lab. 9

S2Net example: max() cont` yy = ff(ww TT xx), (cccccccccccccc vvvvvvvvvvvv yy 2 1 ) sigmoid xx ii yy ii yy ii ff(nnnntt jj ) ssssssssss zz ddddddd, zz ddddddd, max(0, 1 zz ddddddd + zz ddddddd ) yy ii zz ddddddd yy ii yy ii zz dddddd2 score(.) yy ii Intelligent Software Lab. 10

S2Net example: max() cont` Back prop. ssssss zz ddddddd, zz ddddddd mmmmmm 0, nnnnnn = 1 iiii 1 ss + ss cc > 0 0 ooooooooooooooooo gradient update fff nnnnnn = ssssssssssssss. gradient update logistic sigmoid ff nnnnnn = ff nnnnnn nnnnnn 1 1 + exp nnnnnn = ff nnnnnn 1 ff nnnnnn Intelligent Software Lab. 11

Intelligent Software Lab. 12

S2Net example: cosine_sim() Input sentences Sen1: what movies johnny depp is in? Sen2: what movies does johnny depp play in? Sen3: who has been married to julia roberts? Bag of words(size 16): Term vector: Intelligent Software Lab. 13

S2Net example cosine_sim() cont` Weights: (size: d x k) 0.005 0.0015 0.1 0.075 0.12 0.005 0.0015 0.02 0.1 0.05 0.1 0.05 0.1 0.05 0.0005 0.2 0.003 0.2 0.1 0.005 0.1 0.08 0 0.075 0 0.09 0.2 0.076 0.005 0.0125 0.065 0.01 Term vector: ssssssssss ttww (. ) ff = tttttttt vvvvvvvvvvvv tttt, ff = VV, dd 1 rrrrrr vvvvvvvvvvvv AA = αα iiii, αα dd kk iiii AA ( weights) gg = AA TT ff ssssmm AA (ff pp, ff qq ) vvvvvvvvvvvv gg kk 1 ( projected concept vector) Intelligent Software Lab. 14

S2Net example cosine_sim() cont` Term vectors: AA TT : 0.005, 0.1, 0.12, 0.0015, 0.1, 0.1, 0.1, 0.0005, 0.003, 0.1, 0.1, 0, 0, 0.2, 0.005, 0.065 0.0015, 0.075, 0.005, 0.02, 0.05, 0.05, 0.05, 0.2, 0.2, 0.005, 0.08, 0.075, 0.09, 0.076, 0.0125, 0.01 Intelligent Software Lab. 15

S2Net example cosine_sim() cont` gg = AA TT ff (cccccccccccccc vvvvvvvvvvvv gg kk 1 ) ssssmm AA ff pp, ff qq = gg pp TT gg qq gg pp gg qq, (cosine similarity) (aaaaaaaaaaaaaaaaaaaa ffffffffffffffff) Intelligent Software Lab. 16

S2Net example cosine_sim() cont` YY llllllllll llllllll ffffffffffffffff(mmmmmm) = 1 2 yy pppp ssssmm AA ff pp, ff qq 2 Or 0 Intelligent Software Lab. 17

Intelligent Software Lab.

S2Net example3 cosine_sim() activation Input sentences Sen1: what movies johnny depp is in? Sen2: what movies does johnny depp play in? Sen3: who has been married to julia roberts? Bag of words(size 16): Term vector: Intelligent Software Lab. 19

S2Net example3 cosine_sim() activation` Weights: (size: d x k) 0.05 0.05 0.05 0.075 0.1 0.125 0.02 0.075 0.1 0.05 0.005 0.05 0.005 0.05 0.08 0.2 0.125 0.0125 0.1 0.05 0.1 0.025 0.125 0.075 0.115 0.075 0.005 0.05 0.01 0.0155 0.01 0.022 Term vector: ssssssssss ttww (. ) ff = tttttttt vvvvvvvvvvvv tttt, ff = VV, dd 1 rrrrrr vvvvvvvvvvvv AA = αα iiii, αα dd kk iiii AA ( weights) gg = AA TT ff ssssmm AA (ff pp, ff qq ) vvvvvvvvvvvv gg kk 1 ( projected concept vector) Intelligent Software Lab. 20

S2Net example3 cosine_sim() activation` Input vector: AA TT : 0.05, 0.05, 0.1, 0.02, 0.1, 0.005, 0.005, 0.08, 0.125, 0.1, 0.1, 0.125, 0.115, 0.005, 0.01, 0.01 0.05, 0.075, 0.125, 0.075, 0.05, 0.05, 0.05, 0.2, 0.0125, 0.05, 0.025, 0.075, 0.075, 0.05, 0.0155, 0.022 Intelligent Software Lab. 21

S2Net example3 cosine_sim() activation` gg = AA TT ff (cccccccccccccc vvvvvvvvvvvv gg kk 1 ) ssssmm AA ff pp, ff qq = gg pp TT gg qq gg pp gg qq, (cosine similarity) Intelligent Software Lab. 22

S2Net example3 cosine_sim() activation` Y label Intelligent Software Lab. 23