2021-02-01-rel_video - Speaker Deck

Slide 1

Slide 1 text

v3 So fi e Van Landeghem FOR NAMED ENTITY Trainable Component Relation Extraction CUSTOM

Slide 2

Slide 2 text

spacy.io

Slide 3

Slide 3 text

Production-ready training system, model packaging & workflow management spacy.io

Slide 4

Slide 4 text

Models written in any framework Production-ready training system, model packaging & workflow management spacy.io

Slide 5

Slide 5 text

Models written in any framework Multi-task learning with transformers like BERT Production-ready training system, model packaging & workflow management spacy.io

Slide 6

Slide 6 text

Models written in any framework Multi-task learning with transformers like BERT Production-ready training system, model packaging & workflow management Fully custom trainable pipeline components spacy.io

Slide 7

Slide 7 text

No content

Slide 8

Slide 8 text

named entity

Slide 9

Slide 9 text

named entity semantic relationship

Slide 10

Slide 10 text

No content

Slide 11

Slide 11 text

gene or gene product

Slide 12

Slide 12 text

gene or gene product positive regulation

Slide 13

Slide 13 text

Document Machine Learning model Predictions matrix Doc Text ner rel

Slide 14

Slide 14 text

Document Machine Learning model Predictions matrix Doc Text ner rel step #1: implement model

Slide 15

Slide 15 text

Document Machine Learning model Predictions matrix Doc Text ner rel step #1: implement model step #2: implement pipeline component

Slide 16

Slide 16 text

Document Machine Learning model Predictions matrix Doc Text ner rel step #1: implement model step #3:enhance accuracy transformer step #2: implement pipeline component

Slide 17

Slide 17 text

thinc.ai type-checked functional programming API for composing models

Slide 18

Slide 18 text

thinc.ai type-checked functional programming API for composing models wrap layers defined in any framework

Slide 19

Slide 19 text

Document GATA3 inhibits FOXP3 expression

Slide 20

Slide 20 text

Document GATA3 inhibits FOXP3 expression Tokens + NER [GATA3, inhibits, FOXP3, expression]

Slide 21

Slide 21 text

Slide 22

Slide 22 text

Document GATA3 inhibits FOXP3 expression Tokens + NER [GATA3, inhibits, FOXP3, expression] Token vectors [[-0.42, 1.93, -1.08, 0.28, -0.71] [ 3.84, 2.59, -0.14, -3.77, -0.66] [ 3.35, -1.51, 1.23, -0.88, -2.19] [ 3.77, -2.17, -0.48, -1.73, 1.10]] Instance 1 Instance 2 GATA3 -> FOXP3 [-0.42, 1.93, -1.08, 0.28, -0.71, 3.35, -1.51, 1.23, -0.88, -2.19] FOXP3 -> GATA3 [ 3.35, -1.51, 1.23, -0.88, -2.19, -0.42, 1.93, -1.08, 0.28, -0.71]

Slide 23

Slide 23 text

[GATA3, inhibits, FOXP3, expression] Instance data [[-0.42, 1.93, -1.08, 0.28, -0.71, 3.35, -1.51, 1.23, -0.88, -2.19] [ 3.35, -1.51, 1.23, -0.88, -2.19, -0.42, 1.93, -1.08, 0.28, -0.71]]

Slide 24

Slide 24 text

Slide 25

Slide 25 text

Slide 26

Slide 26 text

[GATA3, inhibits, FOXP3, expression] Instance data [[-0.42, 1.93, -1.08, 0.28, -0.71, 3.35, -1.51, 1.23, -0.88, -2.19] [ 3.35, -1.51, 1.23, -0.88, -2.19, -0.42, 1.93, -1.08, 0.28, -0.71]] Classi fi cation layer Relation types: BINDING ACTIVATION INHIBITION GATA3 -> FOXP3 BINDING: False, ACTIVATION: False, INHIBITION: True Instance 1 Instance 2 FOXP3 -> GATA3 BINDING: False, ACTIVATION: False, INHIBITION: False Predictions [[ 0.09, 0.14, 0.93 ] [ 0.11, 0.15, 0.31 ]] BINDING ACTIVATION INHIBITION

Slide 27

Slide 27 text

Documents List[Doc]

Slide 28

Slide 28 text

Documents List[Doc] Token vectors List[Floats2d] tok2vec

Slide 29

Slide 29 text

Documents List[Doc] Token vectors List[Floats2d] tok2vec Entity vectors List[Floats2d] pooling

Slide 30

Slide 30 text

Documents List[Doc] Token vectors List[Floats2d] tok2vec Entity vectors List[Floats2d] pooling Candidate instances List[Tuple[Span, Span]] get_instances

Slide 31

Slide 31 text

create_instance_tensor Instance tensor Floats2d Documents List[Doc] Token vectors List[Floats2d] tok2vec Entity vectors List[Floats2d] pooling Candidate instances List[Tuple[Span, Span]] get_instances

Slide 32

Slide 32 text

create_instance_tensor Instance tensor Floats2d Documents List[Doc] Predictions matrix Floats2d classification layer Token vectors List[Floats2d] tok2vec Entity vectors List[Floats2d] pooling Candidate instances List[Tuple[Span, Span]] get_instances

Slide 33

Slide 33 text

Document TGF-beta signalling induces Id2

Slide 34

Slide 34 text

Document TGF-beta signalling induces Id2 Tokens + NER [TGF, -, beta, signalling, induces, Id2]

Slide 35

Slide 35 text

Slide 36

Slide 36 text

Document TGF-beta signalling induces Id2 Tokens + NER [TGF, -, beta, signalling, induces, Id2] Token vectors [[ 1.22, -3.12, -0.19, 0.51, -0.46] [-1.71, 0.92, -0.67, 0.86, 2.70] [-1.32, 2.52, -0.26, -0.86, -1.74] [-1.27, 2.21, -0.75, 1.07, -0.48] [-1.03, 0.94, 1.64, -0.05, -0.98] [-0.81, 0.72, -0.52, 0.67, -0.16]] Entities Ragged [3, 1, 1, 3] Lengths Data [[ 1.22, -3.12, -0.19, 0.51, -0.46] [-1.71, 0.92, -0.67, 0.86, 2.70] [-1.32, 2.52, -0.26, -0.86, -1.74] [-0.81, 0.72, -0.52, 0.67, -0.16] [-0.81, 0.72, -0.52, 0.67, -0.16] [ 1.22, -3.12, -0.19, 0.51, -0.46] [-1.71, 0.92, -0.67, 0.86, 2.70] [-1.32, 2.52, -0.26, -0.86, -1.74]]

Slide 37

Slide 37 text

Slide 38

Slide 38 text

Slide 39

Slide 39 text

[TGF, -, beta, signalling, induces, Id2] Entities Ragged [3, 1, 1, 3] Lengths Data [[ 1.22, -3.12, -0.19, 0.51, -0.46] [-1.71, 0.92, -0.67, 0.86, 2.70] [-1.32, 2.52, -0.26, -0.86, -1.74] [-0.81, 0.72, -0.52, 0.67, -0.16] [-0.81, 0.72, -0.52, 0.67, -0.16] [ 1.22, -3.12, -0.19, 0.51, -0.46] [-1.71, 0.92, -0.67, 0.86, 2.70] [-1.32, 2.52, -0.26, -0.86, -1.74]] Pooled entities Floats2d [[-0.60, 0.11, -0.37, 0.17, 0.17] [-0.81, 0.72, -0.52, 0.67, -0.16] [-0.81, 0.72, -0.52, 0.67, -0.16] [-0.60, 0.11, -0.37, 0.17, 0.17]] Instance 1 Instance 2

Slide 40

Slide 40 text

[TGF, -, beta, signalling, induces, Id2] Entities Ragged [3, 1, 1, 3] Lengths Data [[ 1.22, -3.12, -0.19, 0.51, -0.46] [-1.71, 0.92, -0.67, 0.86, 2.70] [-1.32, 2.52, -0.26, -0.86, -1.74] [-0.81, 0.72, -0.52, 0.67, -0.16] [-0.81, 0.72, -0.52, 0.67, -0.16] [ 1.22, -3.12, -0.19, 0.51, -0.46] [-1.71, 0.92, -0.67, 0.86, 2.70] [-1.32, 2.52, -0.26, -0.86, -1.74]] Instance tensor Floats2d [[-0.60, 0.11, -0.37, 0.17, 0.17, -0.81, 0.72, -0.52, 0.67, -0.16] [-0.81, 0.72, -0.52, 0.67, -0.16, -0.60, 0.11, -0.37, 0.17, 0.17]] Pooled entities Floats2d [[-0.60, 0.11, -0.37, 0.17, 0.17] [-0.81, 0.72, -0.52, 0.67, -0.16] [-0.81, 0.72, -0.52, 0.67, -0.16] [-0.60, 0.11, -0.37, 0.17, 0.17]] Instance 1 Instance 2

Slide 41

Slide 41 text

optimize model settings for accuracy or efficiency components to train spacy.io/usage/training generate starter config

Slide 42

Slide 42 text

con fi g.cfg structured section describing nlp object

Slide 43

Slide 43 text

con fi g.cfg structured section describing nlp object pipeline component names

Slide 44

Slide 44 text

con fi g.cfg structured section defining components

Slide 45

Slide 45 text

con fi g.cfg structured section defining components factory function used to create component

Slide 46

Slide 46 text

con fi g.cfg structured section defining components factory function used to create component registered function to create model architecture

Slide 47

Slide 47 text

con fi g.cfg structured section defining components factory function used to create component registered function to create model architecture function arguments

Slide 48

Slide 48 text

con fi g.cfg custom factory

Slide 49

Slide 49 text

con fi g.cfg custom factory model architecture

Slide 50

Slide 50 text

con fi g.cfg custom factory sublayers model architecture

Slide 51

Slide 51 text

con fi g.cfg custom factory sublayers model architecture listener layer to connect to tok2vec component

Slide 52

Slide 52 text

spacy.io/usage/layers-architectures

Slide 53

Slide 53 text

predictions reference spacy.io/usage/layers-architectures

Slide 54

Slide 54 text

No content

Slide 55

Slide 55 text

Entities

Slide 56

Slide 56 text

Entities Entity Relations custom attribute

Slide 57

Slide 57 text

github.com/explosion/projects manage and share end-to-end workflows

Slide 58

Slide 58 text

github.com/explosion/projects manage and share end-to-end workflows clone the project template for this tutorial

Slide 59

Slide 59 text

transformer component spacy.io/usage/embeddings-transformers con fi g.cfg

Slide 60

Slide 60 text

use any pretrained transformer models transformer component spacy.io/usage/embeddings-transformers con fi g.cfg

Slide 61

Slide 61 text

con fi g.cfg spacy.io/usage/embeddings-transformers

Slide 62

Slide 62 text

listener layer to connect to transformer component con fi g.cfg spacy.io/usage/embeddings-transformers

Slide 63

Slide 63 text

spacy.io/usage/v3 @spacy_io install spaCy v3 @OxyKodit

Slide 64

Slide 64 text

spacy.io/usage/v3 @spacy_io documentation and quickstart install spaCy v3 @OxyKodit

Slide 65

Slide 65 text

spacy.io/usage/v3 @spacy_io documentation and quickstart install spaCy v3 clone the project template @OxyKodit

Slide 66

Slide 66 text

spacy.io/usage/v3 @spacy_io documentation and quickstart install spaCy v3 thank you! — clone the project template @OxyKodit

Slide 67

Slide 67 text

No content