○○2vec 再考 - Speaker Deck

Slide 1

Slide 1 text

Slide 2

Slide 2 text

Slide 3

Slide 3 text

Slide 4

Slide 4 text

Slide 5

Slide 5 text

Slide 6

Slide 6 text

Slide 7

Slide 7 text

Slide 8

Slide 8 text

Slide 9

Slide 9 text

Slide 10

Slide 10 text

Slide 11

Slide 11 text

Slide 12

Slide 12 text

Slide 13

Slide 13 text

Slide 14

Slide 14 text

©2019 Wantedly, Inc. w ෳࡶͳੑ࣭΍ؔ܎ੑ͕ѻ͍΍͘͢ͳΔ w l୯ޠͷҙຯzͷΑ͏ͳෳࡶͰந৅తͳ΋ͷ͸ѻ͍ͮΒ͍ w lϕΫτϧz͸ͨͩͷ਺ࣈͳͷͰ؆୯ʂ w Entityͷੑ࣭ɺEntityؒͷؔ܎ੑ͕਺ࣈͰදݱͰ͖Δ w ϕΫτϧʹ͸Entityͷੑ࣭͕ຒΊࠐ·Ε͍ͯΔʢ͸ͣʣ w ϕΫτϧಉ࢜ͷԋࢉͰEntityؒͷؔ܎ੑ͕දͤΔ w ࣅ͍ͯΔॱʹ୯ޠΛฒͼସ͑Δͱ͍ͬͨૢ࡞͕ՄೳʹͳΔ ○○2vec֓ཁ ͳʹ͕͏Ε͍͠ͷ͔

Slide 15

Slide 15 text

Slide 16

Slide 16 text

Slide 17

Slide 17 text

Slide 18

Slide 18 text

Slide 19

Slide 19 text

Slide 20

Slide 20 text

Slide 21

Slide 21 text

Slide 22

Slide 22 text

Slide 23

Slide 23 text

Slide 24

Slide 24 text

Slide 25

Slide 25 text

Slide 26

Slide 26 text

Slide 27

Slide 27 text

Slide 28

Slide 28 text

Slide 29

Slide 29 text

Slide 30

Slide 30 text

Slide 31

Slide 31 text

Slide 32

Slide 32 text

Slide 33

Slide 33 text

Slide 34

Slide 34 text

Slide 35

Slide 35 text

Slide 36

Slide 36 text

Slide 37

Slide 37 text

Slide 38

Slide 38 text

Slide 39

Slide 39 text

Slide 40

Slide 40 text

Slide 41

Slide 41 text

Slide 42

Slide 42 text

Slide 43

Slide 43 text

Slide 44

Slide 44 text

Slide 45

Slide 45 text

Slide 46

Slide 46 text

Slide 47

Slide 47 text

Slide 48

Slide 48 text

Slide 49

Slide 49 text

Slide 50

Slide 50 text

Slide 51

Slide 51 text

Slide 52

Slide 52 text

Slide 53

Slide 53 text

Slide 54

Slide 54 text

Slide 55

Slide 55 text

©2019 Wantedly, Inc. • ৽͍͠ϊʔυɺΤοδ͕௥Ճ͞ΕΔͨͼʹશମΛ࠶ֶश͢Δ • ࠩ෼ߋ৽తͳ͜ͱ΋ݚڀ͸͞Ε͍ͯΔ͕େม • ࠶ֶशલͱޙͰ͸ಘΒΕΔϕΫτϧ͸׬શʹผ෺ʹͳΔ • ಉ͡ Entity Ͱ΋·ͬͨ͘ผ෺ʹͳΔ • ؒҧͬͯݹ͍ϕΫτϧͱ৽͍͠ϕΫτϧͰԋࢉ͢ΔͱյΕΔ • ʓʓ2vec ͷޙΖʹผͷϞσϧΛͭͳ͍͛ͯΔ৔߹͸  ͦͷϞσϧ΋ಉ࣌ʹ࠶ֶश͢Δඞཁ͕͋Δ ߋ৽ɺ࠶ֶश͕ͭΒ͍όʔδϣχϯά

Slide 56

Slide 56 text

©2019 Wantedly, Inc. ΑΓޮՌతʹ࢖͏ͨΊʹ • ߴ଎ʹ࡞Εͯͦͦ͜͜༏लͳϕʔεϥΠϯͱͯ͠࢖͏ • ݶΒΕͨϦιʔεͰ੒ՌΛ࠷େԽ͢Δ • ͻͱཻͰ N ౓͓͍͍͠ঢ়ଶΛ࡞Δ • σʔλΛάϥϑతʹѻ͍΍͍͢Α͏ʹͯ͠ੵΈॏͶΔ • ಉ͡ Entity ͕ʮಉ͡ʯͰ͋Δͱѻ͑ΔΑ͏ʹ͓ͯ͘͠ • ͦͷυϝΠϯʹ͓͚Δ Knowledge Base Λ࡞Δ • λεΫʹΑͬͯద੾ͳαϒάϥϑΛఆٛ͢Δ • ҋӢͳϞσϧڞ༗ / άϥϑڞ༗͸͠ͳ͍

Slide 57

Slide 57 text

Slide 58

Slide 58 text

©2019 Wantedly, Inc. ࢀߟจݙ - Efficient Estimation of Word Representations in Vector Space - Tomas Mikolov, et al., 2013, ICLR - https://arxiv.org/abs/1301.3781 - FaceNet: A Unified Embedding for Face Recognition and Clustering - Florian Schroff, et al., 2015, CVPR - https://arxiv.org/abs/1503.03832 - PyTorch-BigGraph: A Large-scale Graph Embedding Framework - Adam Lerer, et al., 2019, SysML - https://arxiv.org/abs/1903.12287 - StarSpace: Embed All The Things! - Ledell Wu, et al. - https://arxiv.org/abs/1709.03856