deep learning & nlp: graphs to the rescue!

Deep Learning & NLPGraphs to the Rescue! (or not yet…)

Roelof Pieters, KTH/CSC, Graph Technologies R&D

roelof@kth.se

Stockholm, Sics, October 21 2014

Twitter: @graphificwww.csc.kth.se/~roelof/

DefinitionsMachine Learning

Improving some task T based on experience E with respect to performance measure P. - T. Mitchell (1997)

Learning denotes changes in the system that are adaptive in the sense that they enable the system to do the same task (or tasks drawn from a population of similar tasks) more effectively the next time. - H. Simon (1983)

DefinitionsRepresentation learning

Attempts to automatically learn good features or representations

Deep learning

Attempt to learn multiple levels of representation of increasing complexity/abstraction

Overview

1. From Machine Learning to Deep Learning

2. Natural Language Processing

3. Graph-Based Approaches to DL+NLP

1. from Machine Learning

to Deep Learning

Perceptron

• Rosenblatt 1957

Perceptron

• Rosenblatt 1957 • Minsky & Papert 1969

Perceptron

• Rosenblatt 1957 • Minsky & Papert 1969

The world believed Minsky & Papert…

2th gen Perceptron• Quest to make it non-linear

• no result…

Until finally…

• Rumelhart, Hinton & Williams, 1986

• Multi-Layered Perceptrons (MLP) !!!

• Backpropagation (Bryson & Ho 1969)(Rumelhart, Hinton & Williams, 1986)

• Forward Propagation :

• Sum inputs, produce activation, feed-forward

• Back Propagation of Error

• Calculate total error at the top

• Calculate contributions to error at each step going backwards

Phase 1: PropagationEach propagation involves the following steps:

1. Forward propagation of a training pattern's input through the neural network in order to generate the propagation's output activations.

2. Backward propagation of the propagation's output activations through the neural network using the training pattern target in order to generate the deltas of all output and hidden neurons.

Phase 2: Weight update For each weight-synapse follow the following steps:

1. Multiply its output delta and input activation to get the gradient of the weight.

2. Subtract a ratio (percentage) of the gradient from the weight.

Perceptron Network: SVM

• Vapnik et al. 1992; 1995.

• Cortes & Vapnik 1995

Source: Cortes & Vapnik 1995

Perceptron Network: SVM

• Vapnik et al. 1992; 1995.

• Cortes & Vapnik 1995

Source: Cortes & Vapnik 1995

Kernel SVM

“2006”

“2006”• Faster machines (GPU’s!)

• More data

“2006”• Faster machines (GPU’s!)

• More data

• New methods for unsupervised pre-training

“2006”• New methods for unsupervised pre-training

• Stacked RBM’s (Deep Belief Networks [DBN’s] )

• Hinton, G. E, Osindero, S., and Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18:1527-1554.

• Hinton, G. E. and Salakhutdinov, R. R, Reducing the dimensionality of data with neural networks. Science, Vol. 313. no. 5786, pp. 504 - 507, 28 July 2006.

• (Stacked) Autoencoders

• Bengio, Y., Lamblin, P., Popovici, P., Larochelle, H. (2007). Greedy Layer-Wise Training of Deep Networks, Advances in Neural Information Processing Systems 19

Pretraining: Stacked RBM’s

• Iterative pre-training construction of Deep Belief Network (DBN) (Hinton et al., 2006)

from: Larochelle et al. (2007). An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation.

Pretraining: Stacked Denoising Auto-encoder

• Stacking Auto-Encoders

from: Bengio ICML 2009

• (Vincent et al, 2008)

• Good vs Corrupted context

from: Vincent et al 2010

from: Vincent et al 2010Raw input

from: Vincent et al 2010Corrupted input Raw input

Hidden code (representation)

Corrupted input Raw input

Corrupted input Raw input reconstruction

KL(reconstruction | raw input)

Convolutional Neural Networks (CNNs) • Fukushima 1980; LeCun et al. 1998; Behnke 2003; Simard et al. 2003…

• Hinton et al. 2006; Bengio et al. 2007; Ranzato et al. 2007

• Sparse connectivity:

• MaxPooling

• Shared weights:

(Figures from http://deeplearning.net/tutorial/lenet.html)

Pretraining• Why does Pretraining work so well? (Erhan et al. 2010)

• Better Generalisation

without unsupervised pretraining with unsupervised pretraining)

Figures from Erhan et al. 2010

Pretraining

Figures from Erhan et al. 2010

–Andrew Ng

“I’ve worked all my life in Machine Learning, and I’ve never seen one algorithm knock over

benchmarks like Deep Learning”

The (god)fathers of DL

DL: (Every)where ?

DL: (Every)where ?• Language Modeling (2012, Mikolov et al)

• Image Recognition (Krizhevsky won 2012 ImageNet competition)

• Sentiment Classification (2011, Socher et al)

• Speech Recognition (2010, Dahl et al)

• MNIST hand-written digit recognition (Ciresan et al, 2010)

So: Why Deep?Deep Architectures can be representationally efficient

• Fewer computational units for same function

Deep Representations might allow for a hierarchy or representation

• Allows non-local generalisation

• Comprehensibility

Multiple levels of latent variables allow combinatorial sharing of statistical strength

So: Why Deep?Generalizing better to new tasks & domains

Can learn good intermediate representations shared across tasks

Distributed representations

Unsupervised Learning

Multiple levels of representation

Diff Levels of Abstraction• Hierarchical Learning

• Natural progression from low level to high level structure as seen in natural complexity

• Easier to monitor what is being learnt and to guide the machine to better subspaces

• A good lower level representation can be used for many distinct tasks

Generalizable Learning• Shared Low Level Representations

• Multi-Task Learning

• Unsupervised Training

Generalizable Learning• Shared Low Level Representations

• Multi-Task Learning

• Unsupervised Training

• Partial Feature Sharing

• Mixed Mode Learning

• Composition of Functions

No More Handcrafted Features !

2. Natural Language Processing

DL + NLP• Language Modeling

• Bengio et al. (2000, 2003): via Neural network

• Mnih and Hinton (2007): via RBMs

• Pos, Chunking, NER, SRL

• Collobert and Weston 2008

• Socher et al 2011; Socher 2014

Language Modeling• Word Embeddings (Bengio et al, 2001; Bengio et

al, 2003) based on idea of distributed representations for symbols (Hinton 1986)

• Neural Word embeddings (Turian et al 2010; Collobert et al. 2011)

Word Embeddings• Collobert & Weston 2008; Collobert et al. 2011

• similar to word vector learning, but uses instead of single scalar score, a Softmax/Maxent classifier

33word embeddings in from lookup table. From Collobert et al. 2011

• similar to word vector learning, but uses instead of single scalar score, a Softmax/Maxent classifier

Figure from Socher et al. Tutorial ACL 2012.

• window approach

36source: Collobert & Weston, Deep Learning for Natural Language Processing. 2009 Nips

• sentence approach

• Multi-task learning

General Deep Architecture for NLP

Basic features

Embeddings

Basic features

Embeddings

Convolution

Basic features

Embeddings

Convolution

Max pooling

Basic features

Embeddings

Convolution

Max pooling

“Supervised” learning

Word Embeddings• Unsupervised Word Representations (Turian et al

• evaluates Brown clusters, C&W (Collobert and Weston 2008) embeddings, and HLBL (Mnih & Hinton, 2009) embeddings of words -> Brown clusters win out with a small margin on both NER and chunking.

• more info: http://metaoptimize.com/projects/wordreprs/

t-SNE visualizations of word embeddings. Left: Number Region; Right: Jobs Region. From Turian et al. 2011

41http://metaoptimize.com/projects/wordreprs/

• Propose a unified neural network architecture, for many NLP tasks:

• part-of-speech tagging, chunking, named entity recognition, and semantic role labeling

• no hand-made input features

• learns internal representations on the basis of vast amounts of mostly unlabeled training data.

Word Embeddings• Recurrent Neural Network (Mikolov et al. 2010;

Mikolov et al. 2013a)

W(‘‘woman")−W(‘‘man") ≃ W(‘‘aunt")−W(‘‘uncle") W(‘‘woman")−W(‘‘man") ≃ W(‘‘queen")−W(‘‘king")

Figures from Mikolov, T., Yih, W., & Zweig, G. (2013). Linguistic Regularities in Continuous Space Word Representations

• Mikolov et al. 2013b

Figures from Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013b). Efficient Estimation of Word Representations in Vector Space

Word Embeddings• Recursive (Tensor) Network (Socher et al. 2011;

Socher 2014)

Vector Space Model

3. Graph-Based Approaches to DL+NLP

• A) NLP “naturally encoded”

• B) Genetic Finite State Machine

• C) Neural net within Graph

Graph-Based NLP

• Graphs have a “natural affinity” with NLP [ feel free to quote me on that ;) ]

• relation-oriented

• index-free adjacency

Whats in a Graph ?

Figure from Buerli & Obispo (2012).

Whats in a Graph ?• Graph Databases: Neo4j, OrientDB, InfoGrid, Titan,

FlockDB, ArangoDB, InfiniteGraph, AllegroGraph, DEX, GraphBase, and HyperGraphDB

• Distributed graph processing toolkits (based on MapReduce, HDFS, and custom BSP engines): Bagel, Hama, Giraph, PEGASUS, Faunus, Flink

• in-memory graph packages designed for massive shared-memory (NetworkX, Gephi, MTGL, Boost, uRika, and STINGER)

A. NLP “naturally encoded”

• Captures:

• Redundancies

• Gapped Subsequences

• Collapsible Structures From Ganesan 2013

• ie: graph-based opinion summarization (Ganesan et al. 2010; Genevan 2013)

Natural Affinity, Say what?

Summarization Graph

59From Ganesan 2013

Natural Affinity?

• Demo time!

B. Finite State Graph• Bastani 2014a; 2014b; 2014c

• Probabilistic feature hierarchy

• Grammatical inference by genetic algorithms

61more info: https://github.com/kbastani/graphify

Figure from Bastani 2014a

Finite State Graph

• Bastani 2014

• training phase:

all figures from Bastani 2014b

Finite State Graph

• Bastani 2014

• training phase:

Finite State Graph

• Bastani 2014

• training phase:

Finite State Graph

• Bastani 2014

• training phase:

• sentimentanalysis

• error: 0.3

Figure from Bastani 2014c

Conceptual Hierarchical Graph

• Demo time!

C. Factor Graph• Factor graph in which the factors themselves contain a deep neural net.

• Factor graph:

• bipartite graph representing the factorization of a function (Kschischang et al. 2001; Frey 2002)

• can combine Bayesian networks (BNs) and Markov random fields (MRFs).

Figure from Frey 2002

Factor Graph• Factor graph with “deep factors” (Mirowski & LeCun 2009)

• Dynamic Time Series modeling

Energy-Based Graph• LeCun et al. 1998, handwriting recognition

system

• “Graph Transformer Networks”

• Instead of normalised HMM, energy based factor graph (without normalization)

• LeCun et al. 2006.

• Energy-Based Learning

and Finally…And finally…

What you’ve all been waiting for…

Which Net is currently the Biggest ?

the Deepest

The most Bad-ass ?

69source: Szegedy et al. Going deeper with convolutions (GoogLeNet ), ILSVRC2014, 19 Sep 2014

Winners of: Large Scale Visual Recognition Challenge 2014

(ILSVRC2014) 19 September 2014

GoogLeNet

Convolution Pooling Softmax Other

GoogLeNet

Inception

Width of inception modules ranges from 256 filters (in early modules) to 1024 in top inception modules. Can remove fully connected layers on top completely Number of parameters is reduced to 5 million

256 480 480 512

512 512 832 832 1024

Computional cost is increased by less than 2X compared to Krizhevsky’s network. (<1.5Bn operations/evaluation)

Classification results on ImageNet 2012

Team Year Place Error (top-5) Uses external data

SuperVision 2012 - 16.4% no

SuperVision 2012 1st 15.3% ImageNet 22k

Clarifai 2013 - 11.7% no

Clarifai 2013 1st 11.2% ImageNet 22k

MSRA 2014 3rd 7.35% no

VGG 2014 2nd 7.32% no

GoogLeNet 2014 1st 6.67% no

Final Detection Results Team Year Place mAP e x t e r n a l

data ensemble c o n t e x t u a l

model approach

UvA-Euvision 2013 1st 22.6% none ? yes F i s h e r vectors

Deep Insight 2014 3rd 40.5% I L S V R C 1 2 Classification + Localization

3 models yes ConvNet

C U H K DeepID-Net

2014 2nd 40.7% I L S V R C 1 2 Classification + Localization

? no ConvNet

GoogLeNet 2014 1st 43.9% I L S V R C 1 2 Classification

6 models no ConvNet

Detection results

source: Szegedy et al. Going deeper with convolutions (GoogLeNet ), ILSVRC2014, 19 Sep 2014

Wanna Play?• cuda-convnet2 (Alex Krizhevsky, Toronto) (c++/

CUDA, optimized for GTX 580) https://code.google.com/p/cuda-convnet2/

• Caffe (Berkeley) (Cuda/OpenCL, Theano, Python) http://caffe.berkeleyvision.org/

• OverFeat (NYU) http://cilvr.nyu.edu/doku.php?id=code:start

Wanna Play?• Theano - CPU/GPU symbolic expression compiler in python

(from LISA lab at University of Montreal). http://deeplearning.net/software/theano/

• Pylearn2 - Pylearn2 is a library designed to make machine learning research easy. http://deeplearning.net/software/pylearn2/

• Torch - provides a Matlab-like environment for state-of-the-art machine learning algorithms in lua (from Ronan Collobert, Clement Farabet and Koray Kavukcuoglu) http://torch.ch/

• more info: http://deeplearning.net/software links/

(slide partially stolen from: J. Sullivan, Convolutional Neural Networks & Computer Vision, Machine Learning meetup at Spotify, Stockholm, June 9

Questions / Discussion … ?

Bibliography: Definitions• Mitchell, T. M. (1997). Machine Learning (1st ed.). New York, NY,

USA: McGraw-Hill, Inc.

• Simon, H.A. (1983). Why should machines learn? in: Machine Learning: An Artificial Intelligence Approach, (R. Michalski, J. Carbonell, T. Mitchell, eds) Tioga Press, 25-38.

Bibliography: History• Rosenblatt, Frank (1957), The Perceptron--a perceiving and recognizing automaton. Report

85-460-1, Cornell Aeronautical Laboratory.

• Minsky & Papert (1969), Perceptrons: an introduction to computational geometry.

• Bryson, A.E.; W.F. Denham; S.E. Dreyfus (1963) Optimal programming problems with inequality constraints. I: Necessary conditions for extremal solutions. AIAA J. 1, 11 2544-2550.

• Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J. (1986). "Learning representations by back-propagating errors". Nature 323 (6088): 533–536.

• Boser, B. E., Guyon, I., and Vapnik, V. (1992). A training algorithm for optimal margin classifiers. In Proceedings of the Fifth Annual Workshop on Computational Learning Theory, pages 144–152. ACM Press.

• Cortes, C. and Vapnik, V. (1995), Support-vector network. Machine Learning, 20:273–297.

• Larochelle, H., Erhan, D., Courville, A., Bergstra, J., & Bengio, Y. (2007). An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation. In Proceedings of the 24th International Conference on Machine Learning (pp. 473–480). New York, NY, USA: ACM.

• Vincent, P., Larochelle, H., & Lajoie, I. (2010), Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research, 11, 3371–3408.

Bibliography: History - CNN’s• Fukushima, Kunihiko (1980). "Neocognitron: A Self-organizing Neural Network Model for a

Mechanism of Pattern Recognition Unaffected by Shift in Position". Biological Cybernetics 36 (4): 193–202. doi:10.1007/BF00344251. PMID 7370364. Retrieved 16 November 2013.

• LeCun, Yann; Léon Bottou; Yoshua Bengio; Patrick Haffner (1998). "Gradient-based learning applied to document recognition". Proceedings of the IEEE 86 (11): 2278–2324.

• S. Behnke. Hierarchical Neural Networks for Image Interpretation, volume 2766 of Lecture Notes in Computer Science. Springer, 2003.

• Simard, Patrice, David Steinkraus, and John C. Platt. "Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis." In ICDAR, vol. 3, pp. 958-962. 2003.

• Hinton, GE; Osindero, S; Teh, YW (Jul 2006). "A fast learning algorithm for deep belief nets.". Neural computation 18 (7): 1527–54.

• Bengio, Yoshua; Lamblin, Pascal; Popovici, Dan; Larochelle, Hugo (2007). "Greedy Layer-Wise Training of Deep Networks". Advances in Neural Information Processing Systems: 153–160.

• Ranzato, MarcAurelio; Poultney, Christopher; Chopra, Sumit; LeCun, Yann (2007). "Efficient Learning of Sparse Representations with an Energy-Based Model". Advances in Neural Information Processing Systems.

Bibliography: DL• Bengio, Y., Ducharme, R., & Vincent, P. (2001). A Neural Probabilistic Language Model.

In T. K. Leen & T. G. Dietterich (Eds.), Advances in Neural Information Processing Systems 13 (NIPS’00). MIT Press.

• Bengio, Y., Ducharme, R., Vincent, P., & Janvin, C. (2003). A Neural Probabilistic Language Model. The Journal of Machine Learning Research, 3, 1137–1155.

• Bengio, Y., Lamblin, P., Popovici, P., Larochelle, H. (2007). Greedy Layer-Wise Training of Deep Networks, Advances in Neural Information Processing Systems 19

• Hinton, G. E. (1986). Learning distributed representations of concepts. In Proceedings of the eighth annual conference of the cognitive science society (Vol. 1, p. 12).

• Hinton, G. E. and Salakhutdinov, R. R, (2006) Reducing the dimensionality of data with neural networks. Science, Vol. 313. no. 5786, pp. 504 - 507, 28 July 2006.

• Hinton, G. E, Osindero, S., and Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18:1527-1554.

• Erhan, D., Bengio, Y., & Courville, A. (2010). Why does unsupervised pre-training help deep learning? Journal of Machine Learning Research, 11, 625–660.

Bibliography: DL• P. Vincent, P., Larochelle, H., Bengio, Y. and Manzagol, P. A. (2008) Extracting and

composing robust features with denoising autoencoders. In ICML.

• Vincent, P., Larochelle, H., & Lajoie, I. (2010). Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research, 11, 3371–3408. Bengui 2009

• Krizhevsky, A., Sutskever, I. and Hinton, G. E. (2012) Imagenet classification with deep convolutional neural networks. In NIPS.

• Socher, Richard, Jeffrey Pennington, Eric H. Huang, Andrew Y. Ng, and Christopher D. Manning. (2011). Semi-supervised recursive autoencoders for predict- ing sentiment distributions. In Proceedings of the 2011 Conference on Empiri- cal Methods in Natural Language Processing (EMNLP).

• Dahl, G. E., Ranzato, M. A., Mohamed, A. and Hinton, G. E. (2010) Phone recognition with the mean-covariance restricted Boltzmann machine. In NIPS.

• Ciresan, D. C., Meier, U., Gambardella, L. M., & Schmidhuber, J. (2010). Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition. CoRR.

• Szegedy et al. (2014) Going deeper with convolutions (GoogLeNet ), ILSVRC2014, 19 Sep 2014

Bibliography: NLP• Turian, J., Ratinov, L., & Bengio, Y. (2010). Word Representations: A Simple and

General Method for Semi-supervised Learning. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (pp. 384–394). Stroudsburg, PA, USA: Association for Computational Linguistics.

• Collobert, R., & Weston, J. (2008). A unified architecture for natural language processing: Deep neural networks with multitask learning. Proceedings of the 25th International Conference ….

• Collobert, R., Weston, J., & Bottou, L. (2011). Natural language processing (almost) from scratch. The Journal of Machine Learning Research, 12:2493-2537.

• Collobert & Weston, Deep Learning for Natural Language Processing (2009) Nips Tutorial

• Mikolov, T., Yih, W., & Zweig, G. (2013a). Linguistic Regularities in Continuous Space Word Representations. HLT-NAACL, (June), 746–751.

• Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013b). Efficient Estimation of Word Representations in Vector Space, 1–12. Computation and Language.

• Bengio, Y. and Bengio, S (2000) Modeling high- dimensional discrete data with multi-layer neural networks. In Proceedings of NIPS 12

• Mnih, A. and Hinton, G. E. (2007) Three New Graphical Models for Statistical Language Modelling. International Conference on Machine Learning, Corvallis, Oregon.

• Socher, R., Bengio, Y., & Manning, C. (2012). Deep Learning for NLP (without Magic). Tutorial Abstracts of ACL 2012.

• Socher, R. (2014). recursive deep learning for natural language processing and computer vision. Dissertation.

Bibliography: NLP

Bibliography: Graph-Based Approaches

• Frey, B. (2002). Extending factor graphs so as to unify directed and undirected graphical models. Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence 19 (UAI 03), Morgan Kaufmann, CA, Acapulco, Mexico, 257–264.

• F. R. Kschischang, B. J. Frey, H. A. L. (2001). Factor graphs and the sum-product algorithm. IEEE Transactions on Information Theory, 47(2), 498–519.

• Mirowski, P., & LeCun, Y. (2009). Dynamic factor graphs for time series modeling. Machine Learning and Knowledge Discovery.

• LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE November 1998.

• LeCun, Y., Chopra, S., Hadsell, R., Ranzato, M. A., & Huang, F. J. (2006). A Tutorial on Energy-Based Learning 1 Introduction : Energy-Based Models, 1–59.

Bibliography: Graph-Based Approaches• Buerli, M., & Obispo, C. (2012). The current state of graph databases.

Department of Computer Science, Cal Poly San Luis Obispo

• Ganesan, K., Zhai, C., & Han, J. (2010). Opinosis: a graph-based approach to abstractive summarization of highly redundant opinions. Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), (August), 340–348.

• Ganesan, K. (2013). Opinion Driven Decision Support System. PhD Dissertation, University of Illinois.

• Bastani, K. 2014a, Hierarchical Pattern Recognition, Blog: Meaning Of, June 17, 2014

• Bastani, K. 2014b, Using a Graph Database for Deep Learning Text Classification, Blog: Meaning Of, August 26, 2014

• Bastani, K. 2014c, Deep Learning Sentiment Analysis for Movie Reviews using Neo4j, Blog: Meaning Of, September 15, 2014

deep learning & nlp: graphs to the rescue!

Presentations & Public Speaking

nlp mastering nlp coaching skills.pdf

nlp thema nlp diplom betriebswirt michael büchler

ИСПОЛЬЗОВАНИЕ ПОДХОДА graph2vec ДЛЯ...

n-gram graphs: a generic machine learning tool in the...

n-gram graphs: a generic machine learning tool in the...

nlp practitioner heart of nlp - nlp courses

nlp practitioner workbook business nlp training.uk

construction of multi - dimensional knowledge graphs ·...

introduction to nlp - ils · 1. what is nlp? 2. some...

semantic graphs - university of notre...

nlp-10005586(1-2018) · nlp businessnlp nlp...

zertifizierte ausbildung - nlp - ausbildungen in nlp, zum...

technical rescue · 2019-04-01 · - rope rescue - confined...

nlp practitioner 'plus' infomappe · nlp • nlp...

carlos salgado, 20 jahre nlp - erfahrung nlp...

cs11-711 advanced nlp nlp experimental design

nlp diploma + nlp...

nlp michael hall - the spirit of nlp

improving recall for conjunctive queries on nlp graphs

the evolution of nlp - welcome to gwiz nlp - gwiz nlp