SlideShare a Scribd company logo
1 of 39
Download to read offline
Detecting Paraphrases Using Recursive Autoencoders 1
Machine Learning Group RCC
University of Cambridge
Feynman Liang
5 Nov, 2015
1
Socher et al., Dynamic Pooling and Unfolding Recursive Autoencoders for
Paraphrase Detection (NIPS 2011)
F. Liang Cambridge MLG RCC 5 Nov, 2015 1 / 39
Example
The judge also refused to postpone the trial date of Sept. 29.
Obus also denied a defense motion to postpone the September trial
date.
F. Liang Cambridge MLG RCC 5 Nov, 2015 2 / 39
Paraphrase detection problem
Given: Sentences v1:m, w1:n ∈ V∗
Task: Classify whether v1:m and w1:n are paraphrases of each other
F. Liang Cambridge MLG RCC 5 Nov, 2015 3 / 39
Applications
Plagarism Detection
Text Summarization
Information Retrieval
Re-examining Machine Translation Metrics for Paraphrase Identif cation
Nitin Madnani Joel Tetreault
Educational Testing Service
Princeton, NJ, USA
{ nmadnani,jtetreault} @ets.org
F. Liang Cambridge MLG RCC 5 Nov, 2015 4 / 39
Outline
Distributed Word Representations
Unfolding recursive autoencoders
Dynamic pooling
Results
Follow-up work
F. Liang Cambridge MLG RCC 5 Nov, 2015 5 / 39
Distributed word representations
F. Liang Cambridge MLG RCC 5 Nov, 2015 6 / 39
Distributional semantics
Goal: Construct a represenation for language which captures semantic
meaning and is convenient for computation
From linguistics:
Lexical/compositional semantics: meaning through individual words
and syntactic constructions (WordNet, formal language theory)
Distributional semantics: meaning through statistical properties (large
datasets, linear algebra)
Distributional hypothesis2
: “A word is characterized by the company it
keeps”
One way to do so is to model join density p(w1:T ) for w1:T ∈ V∗
2
Firth, Studies in Linguistic Analysis 1957
F. Liang Cambridge MLG RCC 5 Nov, 2015 7 / 39
Curse of dimensionality
English language actually has > 106 words, but for simplicity’s sake:
|V| = 105
, w1:10 ∈ V∗
How many free parameters could we potentially need to represent
p(w1:10)?
F. Liang Cambridge MLG RCC 5 Nov, 2015 8 / 39
Simplifying assumption
O(|V|n) is intractable.
Dependencies between words tend to exist only within a local context
=⇒ factorization into CPDs:
P(w1:T ) ≈
T
t=1
P(wt|contextt ⊂ w1:t−1wt+1:n)
For example:
n-gram: context = wi−n+1:i−1
Continuous Bag of Words (word2vec)3: context = wi−4:i+4
3
Mikolov, ICLR 2013
F. Liang Cambridge MLG RCC 5 Nov, 2015 9 / 39
Distributed representation for words
From Bengio, JMLR 2003:
1 Associate with each word in the vocabulary a distributed
word feature vector (w ∈ RD)
2 Express the joint probability function of word sequences in
terms of the feature vectors of these words in the sequence,
and
3 Learn simultaneously the word feature vectors and the
parameters of that probability function
Embedding Matrix Le : V → RD
Joint PDF P(w1:T )
P(w1:T ) =
T
t=1
P(wt|Le(wt−n+1:t−1))
What are we taking the context to be? How many parameters does
P(w1:T ) have?
F. Liang Cambridge MLG RCC 5 Nov, 2015 10 / 39
Neural-network parameterization of CPD
Number free parameters ∈ O(n + D|V|)
J (θ) = 1
T t [− log P(wt|Le(wt−n+1:t−1), θ)] + R(θ)
Bengio, JMLR 2003
F. Liang Cambridge MLG RCC 5 Nov, 2015 11 / 39
A “semantic” vector space
Empirically5:
Words with similar meaning are mapped close together
Directions in the vector space correspond to semantic concepts
Figure: “gender” and “singular/plural” vector offsets from word analogy task
5
Mikolov, NAACL 2013
F. Liang Cambridge MLG RCC 5 Nov, 2015 12 / 39
Unfolding Recursive Autoencoders
F. Liang Cambridge MLG RCC 5 Nov, 2015 13 / 39
From words to sentences
Le : V → RD embeds words into a semantic vector space where the metric
approximates semantic similarity.
If instead we had a V∗ → RD for sentences, then we can measure sentence
similarity and detect paraphrases. . .
F. Liang Cambridge MLG RCC 5 Nov, 2015 14 / 39
Autoencoders
Learn a compact representation
capturing regularities present in the
input
h = se(Wex + be), ˆx = sd (Wd h + bd )
min
We ,Wd
ˆx − x 2
l2
+ R(We, Wd , bd )
Denoising:
h = se(We(x + δ) + be)
Stacking
Application in DNNs6: greedy
layer-wise pretraining +
discriminative fine-tuning
6
Bengio, NIPS 2007
A. Ng., CS294A Lecture notes
F. Liang Cambridge MLG RCC 5 Nov, 2015 15 / 39
Recursive autoencoders for sentence embedding
(RD)∗ → RD: recursively apply RD × RD → RD
yi = f (We[xj ; xk] + b)
f , activation function
Free parameters:
We ∈ RD×2D
, encoding matrix
b ∈ RD
, bias
Anything missing from this definition?
F. Liang Cambridge MLG RCC 5 Nov, 2015 16 / 39
Associativity
Associativity of the binary operation is provided by a grammatical parse
tree (e.g. obtained from CoreNLP8):
8
Klein (ACL 2003)
F. Liang Cambridge MLG RCC 5 Nov, 2015 17 / 39
Training recursive autoencoders
Wd “undoes” We (minimizes square reconstruction error)
To train:
argminWe ,Wd
[x1; y1] − [x1; y1] 2
2
+ R(We, Wd )
Notice anything asymmetrical? (hint: is this even an autoencoder?)
F. Liang Cambridge MLG RCC 5 Nov, 2015 18 / 39
Unfolding RAEs
Reconstruction error was only measured against a single decoding step!
Instead, recursively apply Wd to decode down to terminals
argminWe ,Wd
[xi ; . . . ; xj ] − [xi ; . . . ; xj ] 2
2
+ R(We, Wd )
Children with larger subtrees weighted more
DAG =⇒ efficiently optimized via back-propogation through
structure9 and L-BFGS
9
Goller, 1995
F. Liang Cambridge MLG RCC 5 Nov, 2015 19 / 39
Dynamic pooling
F. Liang Cambridge MLG RCC 5 Nov, 2015 20 / 39
Measuring sentence similarity
From sentence x1:N and RAE encoding y1:K , form
s = [x1, . . . , xN, y1, . . . , yK ]
For two sentences s1, s2, the similarity matrix S has entries
(S)i,j = (s1)i − (s2)j
2
2
F. Liang Cambridge MLG RCC 5 Nov, 2015 21 / 39
Handling varying sentence length
Sentence lengths may vary =⇒ S dimensionality may vary.
Would like S → Spooled ∈ Rnp×np with np constant.
F. Liang Cambridge MLG RCC 5 Nov, 2015 22 / 39
Pooling layers
Used in CNNs to achieve translation invariance
http://ufldl.stanford.edu/tutorial/supervised/ConvolutionalNeuralNetwork/
F. Liang Cambridge MLG RCC 5 Nov, 2015 23 / 39
Dynamic pooling of the similarity matrix
Dynamically partition rows and columns of S into np equal parts
Min. pool (why?) over each part
Normalize µ = 0, σ = 1 and pass on to classifier
F. Liang Cambridge MLG RCC 5 Nov, 2015 24 / 39
Results
F. Liang Cambridge MLG RCC 5 Nov, 2015 25 / 39
Qualitative evaluation of unsupervised feature learning
Dataset
150,000 sentences from NYT and AP sections of Gigaword corpus for
RAE training
Setup
R100 off-the-shelf feature vectors for word embeddings11
Stanford parser12 to extract parse tree
Baseline
Recursive average of all word vectors in parse tree
11
Turian, ACL 2010
12
Klein, ACL 2003
F. Liang Cambridge MLG RCC 5 Nov, 2015 26 / 39
Nearest Spooled neighbor
Figure: Nearest 2-norm neighbor
F. Liang Cambridge MLG RCC 5 Nov, 2015 27 / 39
Recursive decoding
Figure: Unfolding RAE encode/decode
F. Liang Cambridge MLG RCC 5 Nov, 2015 28 / 39
Paraphrase detection task
Dataset
Microsoft Research paraphrase corpus (MSRP)13
5,801 sentence pairs, 3,900 labeled as paraphrases
13
Dolan, COLING 2004
F. Liang Cambridge MLG RCC 5 Nov, 2015 29 / 39
Paraphrase detection task
Setup
4,076 training pairs (67.5% positive), 1,725 test pairs (66.5%
positive)
∀(S1, S2) ∈ D, (S2, S1) also added
Add features ∈ {0, 1} to Spooled related to the set of numbers in S1
and S2
Numbers in S1 = numbers in S2
(Numbers in S1 ∪ numbers in S2) = ∅
Numbers in one sentence ⊂ numbers in other
Softmax classifier over Spooled
F. Liang Cambridge MLG RCC 5 Nov, 2015 30 / 39
Example results
F. Liang Cambridge MLG RCC 5 Nov, 2015 31 / 39
Numerical results
Recursive averaging: 75.9%
Standard RAE: 75.5%
Unfolding RAE: 76.8%
F. Liang Cambridge MLG RCC 5 Nov, 2015 32 / 39
State of the art
“Paraphrase Identification (State of the Art).” ACLWiki. Web. 2 Nov 2015.
F. Liang Cambridge MLG RCC 5 Nov, 2015 33 / 39
Does the dynamic pooling layer add anything?
S-histogram 73.0%
Only added number features 73.2%
Only Spooled 72.6%
Top URAE Node 74.2%
Spooled + number features 76.8%
Is anything suspicious about these results?
F. Liang Cambridge MLG RCC 5 Nov, 2015 34 / 39
Follow-Up Work Since 2011
F. Liang Cambridge MLG RCC 5 Nov, 2015 35 / 39
Extending RAEs to capture compositionality
Recursive Matrix-Vector Spaces15
p = f We
c1
c2
+ b → p = f We
Ba + b0
Ab + a0
+ p0
15
Socher, EMNLP 2012
F. Liang Cambridge MLG RCC 5 Nov, 2015 36 / 39
Encoding the parse tree using LSTMs
Tree-Structured LSTMs16
x1 x2 x3 x4
y1 y2 y3 y4
x1
x2
x4 x5 x6
y1
y2 y3
y4 y6
16
Tai, ACL 2015
F. Liang Cambridge MLG RCC 5 Nov, 2015 37 / 39
Different “semantic norms” on the word vector space
Neural Tensor Networks17
g(e1, R, e2) = uT
R f eT
1 W
[1:k]
R e2 + VR
e1
e2
+ bR
Francesco
Guicciardini
historian male
ItalyFlorence
Francesco
Patrizi
Matteo
Rosselli
profession
gender
place of birth
nationality
location nationality
nationality
gender
17
Socher, NIPS 2013
F. Liang Cambridge MLG RCC 5 Nov, 2015 38 / 39
Questions?

More Related Content

What's hot

Interactive Latent Dirichlet Allocation
Interactive Latent Dirichlet AllocationInteractive Latent Dirichlet Allocation
Interactive Latent Dirichlet AllocationQuentin Pleplé
 
Introduction to R for Data Science :: Session 7 [Multiple Linear Regression i...
Introduction to R for Data Science :: Session 7 [Multiple Linear Regression i...Introduction to R for Data Science :: Session 7 [Multiple Linear Regression i...
Introduction to R for Data Science :: Session 7 [Multiple Linear Regression i...Goran S. Milovanovic
 
Teaching algebra through functional programming
Teaching algebra through functional programmingTeaching algebra through functional programming
Teaching algebra through functional programmingRobert Lee
 
Align, Disambiguate and Walk : A Unified Approach forMeasuring Semantic Simil...
Align, Disambiguate and Walk  : A Unified Approach forMeasuring Semantic Simil...Align, Disambiguate and Walk  : A Unified Approach forMeasuring Semantic Simil...
Align, Disambiguate and Walk : A Unified Approach forMeasuring Semantic Simil...Koji Matsuda
 
A Concurrent Language for Argumentation: Preliminary Notes
A Concurrent Language for Argumentation: Preliminary NotesA Concurrent Language for Argumentation: Preliminary Notes
A Concurrent Language for Argumentation: Preliminary NotesCarlo Taticchi
 
深層意味表現学習 (Deep Semantic Representations)
深層意味表現学習 (Deep Semantic Representations)深層意味表現学習 (Deep Semantic Representations)
深層意味表現学習 (Deep Semantic Representations)Danushka Bollegala
 
Harnessing Deep Neural Networks with Logic Rules
Harnessing Deep Neural Networks with Logic RulesHarnessing Deep Neural Networks with Logic Rules
Harnessing Deep Neural Networks with Logic RulesSho Takase
 
A Unifying Four-State Labelling Semantics for Bridging Abstract Argumentation...
A Unifying Four-State Labelling Semantics for Bridging Abstract Argumentation...A Unifying Four-State Labelling Semantics for Bridging Abstract Argumentation...
A Unifying Four-State Labelling Semantics for Bridging Abstract Argumentation...Carlo Taticchi
 
Machine Learning : Latent variable models for discrete data (Topic model ...)
Machine Learning : Latent variable models for discrete data (Topic model ...)Machine Learning : Latent variable models for discrete data (Topic model ...)
Machine Learning : Latent variable models for discrete data (Topic model ...)Yukara Ikemiya
 
Adaptation of Multilingual Transformer Encoder for Robust Enhanced Universal ...
Adaptation of Multilingual Transformer Encoder for Robust Enhanced Universal ...Adaptation of Multilingual Transformer Encoder for Robust Enhanced Universal ...
Adaptation of Multilingual Transformer Encoder for Robust Enhanced Universal ...Jinho Choi
 
A Study Of Statistical Models For Query Translation :Finding A Good Unit Of T...
A Study Of Statistical Models For Query Translation :Finding A Good Unit Of T...A Study Of Statistical Models For Query Translation :Finding A Good Unit Of T...
A Study Of Statistical Models For Query Translation :Finding A Good Unit Of T...iyo
 
Natural Language Generation in the Wild
Natural Language Generation in the WildNatural Language Generation in the Wild
Natural Language Generation in the WildDaniel Beck
 
4 informed-search
4 informed-search4 informed-search
4 informed-searchMhd Sb
 
A Labelling Semantics for Weighted Argumentation Frameworks
A Labelling Semantics for Weighted Argumentation FrameworksA Labelling Semantics for Weighted Argumentation Frameworks
A Labelling Semantics for Weighted Argumentation FrameworksCarlo Taticchi
 
A Matrix Based Approach for Weighted Argumentation Frameworks
A Matrix Based Approach for Weighted Argumentation FrameworksA Matrix Based Approach for Weighted Argumentation Frameworks
A Matrix Based Approach for Weighted Argumentation FrameworksCarlo Taticchi
 
Extending Labelling Semantics to Weighted Argumentation Frameworks
Extending Labelling Semantics to Weighted Argumentation FrameworksExtending Labelling Semantics to Weighted Argumentation Frameworks
Extending Labelling Semantics to Weighted Argumentation FrameworksCarlo Taticchi
 

What's hot (19)

Interactive Latent Dirichlet Allocation
Interactive Latent Dirichlet AllocationInteractive Latent Dirichlet Allocation
Interactive Latent Dirichlet Allocation
 
Introduction to R for Data Science :: Session 7 [Multiple Linear Regression i...
Introduction to R for Data Science :: Session 7 [Multiple Linear Regression i...Introduction to R for Data Science :: Session 7 [Multiple Linear Regression i...
Introduction to R for Data Science :: Session 7 [Multiple Linear Regression i...
 
Teaching algebra through functional programming
Teaching algebra through functional programmingTeaching algebra through functional programming
Teaching algebra through functional programming
 
Align, Disambiguate and Walk : A Unified Approach forMeasuring Semantic Simil...
Align, Disambiguate and Walk  : A Unified Approach forMeasuring Semantic Simil...Align, Disambiguate and Walk  : A Unified Approach forMeasuring Semantic Simil...
Align, Disambiguate and Walk : A Unified Approach forMeasuring Semantic Simil...
 
Automatic Mathematical Information Retrieval to Perform Translations up to Co...
Automatic Mathematical Information Retrieval to Perform Translations up to Co...Automatic Mathematical Information Retrieval to Perform Translations up to Co...
Automatic Mathematical Information Retrieval to Perform Translations up to Co...
 
A Concurrent Language for Argumentation: Preliminary Notes
A Concurrent Language for Argumentation: Preliminary NotesA Concurrent Language for Argumentation: Preliminary Notes
A Concurrent Language for Argumentation: Preliminary Notes
 
深層意味表現学習 (Deep Semantic Representations)
深層意味表現学習 (Deep Semantic Representations)深層意味表現学習 (Deep Semantic Representations)
深層意味表現学習 (Deep Semantic Representations)
 
Harnessing Deep Neural Networks with Logic Rules
Harnessing Deep Neural Networks with Logic RulesHarnessing Deep Neural Networks with Logic Rules
Harnessing Deep Neural Networks with Logic Rules
 
A Unifying Four-State Labelling Semantics for Bridging Abstract Argumentation...
A Unifying Four-State Labelling Semantics for Bridging Abstract Argumentation...A Unifying Four-State Labelling Semantics for Bridging Abstract Argumentation...
A Unifying Four-State Labelling Semantics for Bridging Abstract Argumentation...
 
Machine Learning : Latent variable models for discrete data (Topic model ...)
Machine Learning : Latent variable models for discrete data (Topic model ...)Machine Learning : Latent variable models for discrete data (Topic model ...)
Machine Learning : Latent variable models for discrete data (Topic model ...)
 
Adaptation of Multilingual Transformer Encoder for Robust Enhanced Universal ...
Adaptation of Multilingual Transformer Encoder for Robust Enhanced Universal ...Adaptation of Multilingual Transformer Encoder for Robust Enhanced Universal ...
Adaptation of Multilingual Transformer Encoder for Robust Enhanced Universal ...
 
A Study Of Statistical Models For Query Translation :Finding A Good Unit Of T...
A Study Of Statistical Models For Query Translation :Finding A Good Unit Of T...A Study Of Statistical Models For Query Translation :Finding A Good Unit Of T...
A Study Of Statistical Models For Query Translation :Finding A Good Unit Of T...
 
Natural Language Generation in the Wild
Natural Language Generation in the WildNatural Language Generation in the Wild
Natural Language Generation in the Wild
 
4 informed-search
4 informed-search4 informed-search
4 informed-search
 
grammer
grammergrammer
grammer
 
Optimization of dfa
Optimization of dfaOptimization of dfa
Optimization of dfa
 
A Labelling Semantics for Weighted Argumentation Frameworks
A Labelling Semantics for Weighted Argumentation FrameworksA Labelling Semantics for Weighted Argumentation Frameworks
A Labelling Semantics for Weighted Argumentation Frameworks
 
A Matrix Based Approach for Weighted Argumentation Frameworks
A Matrix Based Approach for Weighted Argumentation FrameworksA Matrix Based Approach for Weighted Argumentation Frameworks
A Matrix Based Approach for Weighted Argumentation Frameworks
 
Extending Labelling Semantics to Weighted Argumentation Frameworks
Extending Labelling Semantics to Weighted Argumentation FrameworksExtending Labelling Semantics to Weighted Argumentation Frameworks
Extending Labelling Semantics to Weighted Argumentation Frameworks
 

Viewers also liked

Practica 05 jesus garza
Practica 05 jesus garzaPractica 05 jesus garza
Practica 05 jesus garzaprepa mante
 
Odf euromaidan report_eng
Odf euromaidan report_engOdf euromaidan report_eng
Odf euromaidan report_engodfoundation
 
Odf report-destruction-of-independent-journalism-in-ukraine-pl 1
Odf report-destruction-of-independent-journalism-in-ukraine-pl 1Odf report-destruction-of-independent-journalism-in-ukraine-pl 1
Odf report-destruction-of-independent-journalism-in-ukraine-pl 1odfoundation
 
MI MUNDO / Fotografia.
MI MUNDO / Fotografia. MI MUNDO / Fotografia.
MI MUNDO / Fotografia. Pepe Palma
 
13 lecture project management
13 lecture project management13 lecture project management
13 lecture project managementAhmad Basim Hamza
 
Pagrindines unix komandos
Pagrindines unix komandosPagrindines unix komandos
Pagrindines unix komandosDonatas Bukelis
 
13.02.2014 odf ukraine_attacks_on_journalists_pl
13.02.2014 odf ukraine_attacks_on_journalists_pl13.02.2014 odf ukraine_attacks_on_journalists_pl
13.02.2014 odf ukraine_attacks_on_journalists_plodfoundation
 
19.03.2014 odf killed_soldier_krimea_ru
19.03.2014 odf killed_soldier_krimea_ru19.03.2014 odf killed_soldier_krimea_ru
19.03.2014 odf killed_soldier_krimea_ruodfoundation
 
Graduate Marketing Association(GMARK)2015 2016 General Meeting Presentation
Graduate Marketing Association(GMARK)2015 2016 General Meeting PresentationGraduate Marketing Association(GMARK)2015 2016 General Meeting Presentation
Graduate Marketing Association(GMARK)2015 2016 General Meeting PresentationShilpa Mohanty
 
το σχολείο & η πόλη μας!!!
το σχολείο & η πόλη μας!!!το σχολείο & η πόλη μας!!!
το σχολείο & η πόλη μας!!!nouxristina
 
Маленькая история о большом шаге вперед. Социологическая диагностика от "Скоб...
Маленькая история о большом шаге вперед. Социологическая диагностика от "Скоб...Маленькая история о большом шаге вперед. Социологическая диагностика от "Скоб...
Маленькая история о большом шаге вперед. Социологическая диагностика от "Скоб...Скобеев и Партнеры
 
Sprawozdanie merytoryczne 2014
Sprawozdanie merytoryczne 2014Sprawozdanie merytoryczne 2014
Sprawozdanie merytoryczne 2014odfoundation
 
Transmediaal verhalen vertellen
Transmediaal verhalen vertellenTransmediaal verhalen vertellen
Transmediaal verhalen vertellenKirsten_lkca
 
Question one final version 2
Question one final version 2Question one final version 2
Question one final version 2nasimamedia
 
03.03.2014 odf war_russia_ukraine_ru
03.03.2014 odf war_russia_ukraine_ru03.03.2014 odf war_russia_ukraine_ru
03.03.2014 odf war_russia_ukraine_ruodfoundation
 
How to Create a Social Media strategy
How to Create a Social Media strategyHow to Create a Social Media strategy
How to Create a Social Media strategyDebbie O'Connor
 
Gut health - Improving digestion and absorption of food
Gut health - Improving digestion and absorption of foodGut health - Improving digestion and absorption of food
Gut health - Improving digestion and absorption of foodScott Werner
 
Websand - Dublin Tour May 2014
Websand - Dublin Tour May 2014Websand - Dublin Tour May 2014
Websand - Dublin Tour May 2014DDM Alliance
 
SCM Revenue Generation Engines
SCM Revenue Generation EnginesSCM Revenue Generation Engines
SCM Revenue Generation EnginesVictor A. Som
 

Viewers also liked (20)

Dog quotes
Dog quotesDog quotes
Dog quotes
 
Practica 05 jesus garza
Practica 05 jesus garzaPractica 05 jesus garza
Practica 05 jesus garza
 
Odf euromaidan report_eng
Odf euromaidan report_engOdf euromaidan report_eng
Odf euromaidan report_eng
 
Odf report-destruction-of-independent-journalism-in-ukraine-pl 1
Odf report-destruction-of-independent-journalism-in-ukraine-pl 1Odf report-destruction-of-independent-journalism-in-ukraine-pl 1
Odf report-destruction-of-independent-journalism-in-ukraine-pl 1
 
MI MUNDO / Fotografia.
MI MUNDO / Fotografia. MI MUNDO / Fotografia.
MI MUNDO / Fotografia.
 
13 lecture project management
13 lecture project management13 lecture project management
13 lecture project management
 
Pagrindines unix komandos
Pagrindines unix komandosPagrindines unix komandos
Pagrindines unix komandos
 
13.02.2014 odf ukraine_attacks_on_journalists_pl
13.02.2014 odf ukraine_attacks_on_journalists_pl13.02.2014 odf ukraine_attacks_on_journalists_pl
13.02.2014 odf ukraine_attacks_on_journalists_pl
 
19.03.2014 odf killed_soldier_krimea_ru
19.03.2014 odf killed_soldier_krimea_ru19.03.2014 odf killed_soldier_krimea_ru
19.03.2014 odf killed_soldier_krimea_ru
 
Graduate Marketing Association(GMARK)2015 2016 General Meeting Presentation
Graduate Marketing Association(GMARK)2015 2016 General Meeting PresentationGraduate Marketing Association(GMARK)2015 2016 General Meeting Presentation
Graduate Marketing Association(GMARK)2015 2016 General Meeting Presentation
 
το σχολείο & η πόλη μας!!!
το σχολείο & η πόλη μας!!!το σχολείο & η πόλη μας!!!
το σχολείο & η πόλη μας!!!
 
Маленькая история о большом шаге вперед. Социологическая диагностика от "Скоб...
Маленькая история о большом шаге вперед. Социологическая диагностика от "Скоб...Маленькая история о большом шаге вперед. Социологическая диагностика от "Скоб...
Маленькая история о большом шаге вперед. Социологическая диагностика от "Скоб...
 
Sprawozdanie merytoryczne 2014
Sprawozdanie merytoryczne 2014Sprawozdanie merytoryczne 2014
Sprawozdanie merytoryczne 2014
 
Transmediaal verhalen vertellen
Transmediaal verhalen vertellenTransmediaal verhalen vertellen
Transmediaal verhalen vertellen
 
Question one final version 2
Question one final version 2Question one final version 2
Question one final version 2
 
03.03.2014 odf war_russia_ukraine_ru
03.03.2014 odf war_russia_ukraine_ru03.03.2014 odf war_russia_ukraine_ru
03.03.2014 odf war_russia_ukraine_ru
 
How to Create a Social Media strategy
How to Create a Social Media strategyHow to Create a Social Media strategy
How to Create a Social Media strategy
 
Gut health - Improving digestion and absorption of food
Gut health - Improving digestion and absorption of foodGut health - Improving digestion and absorption of food
Gut health - Improving digestion and absorption of food
 
Websand - Dublin Tour May 2014
Websand - Dublin Tour May 2014Websand - Dublin Tour May 2014
Websand - Dublin Tour May 2014
 
SCM Revenue Generation Engines
SCM Revenue Generation EnginesSCM Revenue Generation Engines
SCM Revenue Generation Engines
 

Similar to Detecting paraphrases using recursive autoencoders

Csr2011 june17 15_15_kaminski
Csr2011 june17 15_15_kaminskiCsr2011 june17 15_15_kaminski
Csr2011 june17 15_15_kaminskiCSR2011
 
Dedalo, looking for Cluster Explanations in a labyrinth of Linked Data
Dedalo, looking for Cluster Explanations in a labyrinth of Linked DataDedalo, looking for Cluster Explanations in a labyrinth of Linked Data
Dedalo, looking for Cluster Explanations in a labyrinth of Linked DataVrije Universiteit Amsterdam
 
A Distributed Tableau Algorithm for Package-based Description Logics
A Distributed Tableau Algorithm for Package-based Description LogicsA Distributed Tableau Algorithm for Package-based Description Logics
A Distributed Tableau Algorithm for Package-based Description LogicsJie Bao
 
"That scripting language called Prolog"
"That scripting language called Prolog""That scripting language called Prolog"
"That scripting language called Prolog"Sergei Winitzki
 
A Graph-based Cross-lingual Projection Approach for Spoken Language Understan...
A Graph-based Cross-lingual Projection Approach for Spoken Language Understan...A Graph-based Cross-lingual Projection Approach for Spoken Language Understan...
A Graph-based Cross-lingual Projection Approach for Spoken Language Understan...Seokhwan Kim
 
Incremental View Maintenance for openCypher Queries
Incremental View Maintenance for openCypher QueriesIncremental View Maintenance for openCypher Queries
Incremental View Maintenance for openCypher QueriesopenCypher
 
Higher-order organization of complex networks
Higher-order organization of complex networksHigher-order organization of complex networks
Higher-order organization of complex networksDavid Gleich
 
Latent Dirichlet Allocation
Latent Dirichlet AllocationLatent Dirichlet Allocation
Latent Dirichlet AllocationMarco Righini
 
Paper Summary of Disentangling by Factorising (Factor-VAE)
Paper Summary of Disentangling by Factorising (Factor-VAE)Paper Summary of Disentangling by Factorising (Factor-VAE)
Paper Summary of Disentangling by Factorising (Factor-VAE)준식 최
 
Topic model an introduction
Topic model an introductionTopic model an introduction
Topic model an introductionYueshen Xu
 
Local Model Checking Algorithm Based on Mu-calculus with Partial Orders
Local Model Checking Algorithm Based on Mu-calculus with Partial OrdersLocal Model Checking Algorithm Based on Mu-calculus with Partial Orders
Local Model Checking Algorithm Based on Mu-calculus with Partial OrdersTELKOMNIKA JOURNAL
 
Latent Relational Model for Relation Extraction
Latent Relational Model for Relation ExtractionLatent Relational Model for Relation Extraction
Latent Relational Model for Relation ExtractionGaetano Rossiello, PhD
 
Generating sentences from a continuous space
Generating sentences from a continuous spaceGenerating sentences from a continuous space
Generating sentences from a continuous spaceShuhei Iitsuka
 
N-gram IDF: A Global Term Weighting Scheme Based on Information Distance (WWW...
N-gram IDF: A Global Term Weighting Scheme Based on Information Distance (WWW...N-gram IDF: A Global Term Weighting Scheme Based on Information Distance (WWW...
N-gram IDF: A Global Term Weighting Scheme Based on Information Distance (WWW...Masumi Shirakawa
 
Evaluation of subjective answers using glsa enhanced with contextual synonymy
Evaluation of subjective answers using glsa enhanced with contextual synonymyEvaluation of subjective answers using glsa enhanced with contextual synonymy
Evaluation of subjective answers using glsa enhanced with contextual synonymyijnlc
 
CS571: Distributional semantics
CS571: Distributional semanticsCS571: Distributional semantics
CS571: Distributional semanticsJinho Choi
 
Semantic Parsing with Combinatory Categorial Grammar (CCG)
Semantic Parsing with Combinatory Categorial Grammar (CCG)Semantic Parsing with Combinatory Categorial Grammar (CCG)
Semantic Parsing with Combinatory Categorial Grammar (CCG)shakimov
 
Nelly Litvak – Asymptotic behaviour of ranking algorithms in directed random ...
Nelly Litvak – Asymptotic behaviour of ranking algorithms in directed random ...Nelly Litvak – Asymptotic behaviour of ranking algorithms in directed random ...
Nelly Litvak – Asymptotic behaviour of ranking algorithms in directed random ...Yandex
 
論文紹介:Towards Robust Adaptive Object Detection Under Noisy Annotations
論文紹介:Towards Robust Adaptive Object Detection Under Noisy Annotations論文紹介:Towards Robust Adaptive Object Detection Under Noisy Annotations
論文紹介:Towards Robust Adaptive Object Detection Under Noisy AnnotationsToru Tamaki
 

Similar to Detecting paraphrases using recursive autoencoders (20)

Csr2011 june17 15_15_kaminski
Csr2011 june17 15_15_kaminskiCsr2011 june17 15_15_kaminski
Csr2011 june17 15_15_kaminski
 
Dedalo, looking for Cluster Explanations in a labyrinth of Linked Data
Dedalo, looking for Cluster Explanations in a labyrinth of Linked DataDedalo, looking for Cluster Explanations in a labyrinth of Linked Data
Dedalo, looking for Cluster Explanations in a labyrinth of Linked Data
 
A Distributed Tableau Algorithm for Package-based Description Logics
A Distributed Tableau Algorithm for Package-based Description LogicsA Distributed Tableau Algorithm for Package-based Description Logics
A Distributed Tableau Algorithm for Package-based Description Logics
 
GDRR Opening Workshop - Bayesian Inference for Common Cause Failure Rate Base...
GDRR Opening Workshop - Bayesian Inference for Common Cause Failure Rate Base...GDRR Opening Workshop - Bayesian Inference for Common Cause Failure Rate Base...
GDRR Opening Workshop - Bayesian Inference for Common Cause Failure Rate Base...
 
"That scripting language called Prolog"
"That scripting language called Prolog""That scripting language called Prolog"
"That scripting language called Prolog"
 
A Graph-based Cross-lingual Projection Approach for Spoken Language Understan...
A Graph-based Cross-lingual Projection Approach for Spoken Language Understan...A Graph-based Cross-lingual Projection Approach for Spoken Language Understan...
A Graph-based Cross-lingual Projection Approach for Spoken Language Understan...
 
Incremental View Maintenance for openCypher Queries
Incremental View Maintenance for openCypher QueriesIncremental View Maintenance for openCypher Queries
Incremental View Maintenance for openCypher Queries
 
Higher-order organization of complex networks
Higher-order organization of complex networksHigher-order organization of complex networks
Higher-order organization of complex networks
 
Latent Dirichlet Allocation
Latent Dirichlet AllocationLatent Dirichlet Allocation
Latent Dirichlet Allocation
 
Paper Summary of Disentangling by Factorising (Factor-VAE)
Paper Summary of Disentangling by Factorising (Factor-VAE)Paper Summary of Disentangling by Factorising (Factor-VAE)
Paper Summary of Disentangling by Factorising (Factor-VAE)
 
Topic model an introduction
Topic model an introductionTopic model an introduction
Topic model an introduction
 
Local Model Checking Algorithm Based on Mu-calculus with Partial Orders
Local Model Checking Algorithm Based on Mu-calculus with Partial OrdersLocal Model Checking Algorithm Based on Mu-calculus with Partial Orders
Local Model Checking Algorithm Based on Mu-calculus with Partial Orders
 
Latent Relational Model for Relation Extraction
Latent Relational Model for Relation ExtractionLatent Relational Model for Relation Extraction
Latent Relational Model for Relation Extraction
 
Generating sentences from a continuous space
Generating sentences from a continuous spaceGenerating sentences from a continuous space
Generating sentences from a continuous space
 
N-gram IDF: A Global Term Weighting Scheme Based on Information Distance (WWW...
N-gram IDF: A Global Term Weighting Scheme Based on Information Distance (WWW...N-gram IDF: A Global Term Weighting Scheme Based on Information Distance (WWW...
N-gram IDF: A Global Term Weighting Scheme Based on Information Distance (WWW...
 
Evaluation of subjective answers using glsa enhanced with contextual synonymy
Evaluation of subjective answers using glsa enhanced with contextual synonymyEvaluation of subjective answers using glsa enhanced with contextual synonymy
Evaluation of subjective answers using glsa enhanced with contextual synonymy
 
CS571: Distributional semantics
CS571: Distributional semanticsCS571: Distributional semantics
CS571: Distributional semantics
 
Semantic Parsing with Combinatory Categorial Grammar (CCG)
Semantic Parsing with Combinatory Categorial Grammar (CCG)Semantic Parsing with Combinatory Categorial Grammar (CCG)
Semantic Parsing with Combinatory Categorial Grammar (CCG)
 
Nelly Litvak – Asymptotic behaviour of ranking algorithms in directed random ...
Nelly Litvak – Asymptotic behaviour of ranking algorithms in directed random ...Nelly Litvak – Asymptotic behaviour of ranking algorithms in directed random ...
Nelly Litvak – Asymptotic behaviour of ranking algorithms in directed random ...
 
論文紹介:Towards Robust Adaptive Object Detection Under Noisy Annotations
論文紹介:Towards Robust Adaptive Object Detection Under Noisy Annotations論文紹介:Towards Robust Adaptive Object Detection Under Noisy Annotations
論文紹介:Towards Robust Adaptive Object Detection Under Noisy Annotations
 

More from Feynman Liang

Accelerating Metropolis Hastings with Lightweight Inference Compilation
Accelerating Metropolis Hastings with Lightweight Inference CompilationAccelerating Metropolis Hastings with Lightweight Inference Compilation
Accelerating Metropolis Hastings with Lightweight Inference CompilationFeynman Liang
 
transplantation-isospectral-poster
transplantation-isospectral-postertransplantation-isospectral-poster
transplantation-isospectral-posterFeynman Liang
 
A Unifying Review of Gaussian Linear Models (Roweis 1999)
A Unifying Review of Gaussian Linear Models (Roweis 1999)A Unifying Review of Gaussian Linear Models (Roweis 1999)
A Unifying Review of Gaussian Linear Models (Roweis 1999)Feynman Liang
 
Engineered histone acetylation using DNA-binding domains (DBD), chemical ind...
 Engineered histone acetylation using DNA-binding domains (DBD), chemical ind... Engineered histone acetylation using DNA-binding domains (DBD), chemical ind...
Engineered histone acetylation using DNA-binding domains (DBD), chemical ind...Feynman Liang
 
A LOV2 Domain-Based Optogenetic Tool to Control Protein Degradation and Cellu...
A LOV2 Domain-Based Optogenetic Tool to Control Protein Degradation and Cellu...A LOV2 Domain-Based Optogenetic Tool to Control Protein Degradation and Cellu...
A LOV2 Domain-Based Optogenetic Tool to Control Protein Degradation and Cellu...Feynman Liang
 
Integrated Genomic and Proteomic Analyses of a Systematically Perturbed Metab...
Integrated Genomic and Proteomic Analyses of a Systematically Perturbed Metab...Integrated Genomic and Proteomic Analyses of a Systematically Perturbed Metab...
Integrated Genomic and Proteomic Analyses of a Systematically Perturbed Metab...Feynman Liang
 

More from Feynman Liang (6)

Accelerating Metropolis Hastings with Lightweight Inference Compilation
Accelerating Metropolis Hastings with Lightweight Inference CompilationAccelerating Metropolis Hastings with Lightweight Inference Compilation
Accelerating Metropolis Hastings with Lightweight Inference Compilation
 
transplantation-isospectral-poster
transplantation-isospectral-postertransplantation-isospectral-poster
transplantation-isospectral-poster
 
A Unifying Review of Gaussian Linear Models (Roweis 1999)
A Unifying Review of Gaussian Linear Models (Roweis 1999)A Unifying Review of Gaussian Linear Models (Roweis 1999)
A Unifying Review of Gaussian Linear Models (Roweis 1999)
 
Engineered histone acetylation using DNA-binding domains (DBD), chemical ind...
 Engineered histone acetylation using DNA-binding domains (DBD), chemical ind... Engineered histone acetylation using DNA-binding domains (DBD), chemical ind...
Engineered histone acetylation using DNA-binding domains (DBD), chemical ind...
 
A LOV2 Domain-Based Optogenetic Tool to Control Protein Degradation and Cellu...
A LOV2 Domain-Based Optogenetic Tool to Control Protein Degradation and Cellu...A LOV2 Domain-Based Optogenetic Tool to Control Protein Degradation and Cellu...
A LOV2 Domain-Based Optogenetic Tool to Control Protein Degradation and Cellu...
 
Integrated Genomic and Proteomic Analyses of a Systematically Perturbed Metab...
Integrated Genomic and Proteomic Analyses of a Systematically Perturbed Metab...Integrated Genomic and Proteomic Analyses of a Systematically Perturbed Metab...
Integrated Genomic and Proteomic Analyses of a Systematically Perturbed Metab...
 

Recently uploaded

High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...soniya singh
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Sapana Sha
 
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfMarket Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfRachmat Ramadhan H
 
Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts ServiceSapana Sha
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationshipsccctableauusergroup
 
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptSonatrach
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxJohnnyPlasten
 
Brighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingBrighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingNeil Barnes
 
Aminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
Aminabad Call Girl Agent 9548273370 , Call Girls Service LucknowAminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
Aminabad Call Girl Agent 9548273370 , Call Girls Service Lucknowmakika9823
 
定制英国白金汉大学毕业证(UCB毕业证书) 成绩单原版一比一
定制英国白金汉大学毕业证(UCB毕业证书)																			成绩单原版一比一定制英国白金汉大学毕业证(UCB毕业证书)																			成绩单原版一比一
定制英国白金汉大学毕业证(UCB毕业证书) 成绩单原版一比一ffjhghh
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...Pooja Nehwal
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...Suhani Kapoor
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Callshivangimorya083
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Delhi Call girls
 
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service BhilaiLow Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service BhilaiSuhani Kapoor
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptxthyngster
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfLars Albertsson
 

Recently uploaded (20)

High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
 
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfMarket Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
 
Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts Service
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships
 
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptx
 
Brighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingBrighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data Storytelling
 
Aminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
Aminabad Call Girl Agent 9548273370 , Call Girls Service LucknowAminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
Aminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
 
定制英国白金汉大学毕业证(UCB毕业证书) 成绩单原版一比一
定制英国白金汉大学毕业证(UCB毕业证书)																			成绩单原版一比一定制英国白金汉大学毕业证(UCB毕业证书)																			成绩单原版一比一
定制英国白金汉大学毕业证(UCB毕业证书) 成绩单原版一比一
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
 
E-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptxE-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptx
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
 
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service BhilaiLow Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
 
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdf
 
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
 

Detecting paraphrases using recursive autoencoders

  • 1. Detecting Paraphrases Using Recursive Autoencoders 1 Machine Learning Group RCC University of Cambridge Feynman Liang 5 Nov, 2015 1 Socher et al., Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection (NIPS 2011) F. Liang Cambridge MLG RCC 5 Nov, 2015 1 / 39
  • 2. Example The judge also refused to postpone the trial date of Sept. 29. Obus also denied a defense motion to postpone the September trial date. F. Liang Cambridge MLG RCC 5 Nov, 2015 2 / 39
  • 3. Paraphrase detection problem Given: Sentences v1:m, w1:n ∈ V∗ Task: Classify whether v1:m and w1:n are paraphrases of each other F. Liang Cambridge MLG RCC 5 Nov, 2015 3 / 39
  • 4. Applications Plagarism Detection Text Summarization Information Retrieval Re-examining Machine Translation Metrics for Paraphrase Identif cation Nitin Madnani Joel Tetreault Educational Testing Service Princeton, NJ, USA { nmadnani,jtetreault} @ets.org F. Liang Cambridge MLG RCC 5 Nov, 2015 4 / 39
  • 5. Outline Distributed Word Representations Unfolding recursive autoencoders Dynamic pooling Results Follow-up work F. Liang Cambridge MLG RCC 5 Nov, 2015 5 / 39
  • 6. Distributed word representations F. Liang Cambridge MLG RCC 5 Nov, 2015 6 / 39
  • 7. Distributional semantics Goal: Construct a represenation for language which captures semantic meaning and is convenient for computation From linguistics: Lexical/compositional semantics: meaning through individual words and syntactic constructions (WordNet, formal language theory) Distributional semantics: meaning through statistical properties (large datasets, linear algebra) Distributional hypothesis2 : “A word is characterized by the company it keeps” One way to do so is to model join density p(w1:T ) for w1:T ∈ V∗ 2 Firth, Studies in Linguistic Analysis 1957 F. Liang Cambridge MLG RCC 5 Nov, 2015 7 / 39
  • 8. Curse of dimensionality English language actually has > 106 words, but for simplicity’s sake: |V| = 105 , w1:10 ∈ V∗ How many free parameters could we potentially need to represent p(w1:10)? F. Liang Cambridge MLG RCC 5 Nov, 2015 8 / 39
  • 9. Simplifying assumption O(|V|n) is intractable. Dependencies between words tend to exist only within a local context =⇒ factorization into CPDs: P(w1:T ) ≈ T t=1 P(wt|contextt ⊂ w1:t−1wt+1:n) For example: n-gram: context = wi−n+1:i−1 Continuous Bag of Words (word2vec)3: context = wi−4:i+4 3 Mikolov, ICLR 2013 F. Liang Cambridge MLG RCC 5 Nov, 2015 9 / 39
  • 10. Distributed representation for words From Bengio, JMLR 2003: 1 Associate with each word in the vocabulary a distributed word feature vector (w ∈ RD) 2 Express the joint probability function of word sequences in terms of the feature vectors of these words in the sequence, and 3 Learn simultaneously the word feature vectors and the parameters of that probability function Embedding Matrix Le : V → RD Joint PDF P(w1:T ) P(w1:T ) = T t=1 P(wt|Le(wt−n+1:t−1)) What are we taking the context to be? How many parameters does P(w1:T ) have? F. Liang Cambridge MLG RCC 5 Nov, 2015 10 / 39
  • 11. Neural-network parameterization of CPD Number free parameters ∈ O(n + D|V|) J (θ) = 1 T t [− log P(wt|Le(wt−n+1:t−1), θ)] + R(θ) Bengio, JMLR 2003 F. Liang Cambridge MLG RCC 5 Nov, 2015 11 / 39
  • 12. A “semantic” vector space Empirically5: Words with similar meaning are mapped close together Directions in the vector space correspond to semantic concepts Figure: “gender” and “singular/plural” vector offsets from word analogy task 5 Mikolov, NAACL 2013 F. Liang Cambridge MLG RCC 5 Nov, 2015 12 / 39
  • 13. Unfolding Recursive Autoencoders F. Liang Cambridge MLG RCC 5 Nov, 2015 13 / 39
  • 14. From words to sentences Le : V → RD embeds words into a semantic vector space where the metric approximates semantic similarity. If instead we had a V∗ → RD for sentences, then we can measure sentence similarity and detect paraphrases. . . F. Liang Cambridge MLG RCC 5 Nov, 2015 14 / 39
  • 15. Autoencoders Learn a compact representation capturing regularities present in the input h = se(Wex + be), ˆx = sd (Wd h + bd ) min We ,Wd ˆx − x 2 l2 + R(We, Wd , bd ) Denoising: h = se(We(x + δ) + be) Stacking Application in DNNs6: greedy layer-wise pretraining + discriminative fine-tuning 6 Bengio, NIPS 2007 A. Ng., CS294A Lecture notes F. Liang Cambridge MLG RCC 5 Nov, 2015 15 / 39
  • 16. Recursive autoencoders for sentence embedding (RD)∗ → RD: recursively apply RD × RD → RD yi = f (We[xj ; xk] + b) f , activation function Free parameters: We ∈ RD×2D , encoding matrix b ∈ RD , bias Anything missing from this definition? F. Liang Cambridge MLG RCC 5 Nov, 2015 16 / 39
  • 17. Associativity Associativity of the binary operation is provided by a grammatical parse tree (e.g. obtained from CoreNLP8): 8 Klein (ACL 2003) F. Liang Cambridge MLG RCC 5 Nov, 2015 17 / 39
  • 18. Training recursive autoencoders Wd “undoes” We (minimizes square reconstruction error) To train: argminWe ,Wd [x1; y1] − [x1; y1] 2 2 + R(We, Wd ) Notice anything asymmetrical? (hint: is this even an autoencoder?) F. Liang Cambridge MLG RCC 5 Nov, 2015 18 / 39
  • 19. Unfolding RAEs Reconstruction error was only measured against a single decoding step! Instead, recursively apply Wd to decode down to terminals argminWe ,Wd [xi ; . . . ; xj ] − [xi ; . . . ; xj ] 2 2 + R(We, Wd ) Children with larger subtrees weighted more DAG =⇒ efficiently optimized via back-propogation through structure9 and L-BFGS 9 Goller, 1995 F. Liang Cambridge MLG RCC 5 Nov, 2015 19 / 39
  • 20. Dynamic pooling F. Liang Cambridge MLG RCC 5 Nov, 2015 20 / 39
  • 21. Measuring sentence similarity From sentence x1:N and RAE encoding y1:K , form s = [x1, . . . , xN, y1, . . . , yK ] For two sentences s1, s2, the similarity matrix S has entries (S)i,j = (s1)i − (s2)j 2 2 F. Liang Cambridge MLG RCC 5 Nov, 2015 21 / 39
  • 22. Handling varying sentence length Sentence lengths may vary =⇒ S dimensionality may vary. Would like S → Spooled ∈ Rnp×np with np constant. F. Liang Cambridge MLG RCC 5 Nov, 2015 22 / 39
  • 23. Pooling layers Used in CNNs to achieve translation invariance http://ufldl.stanford.edu/tutorial/supervised/ConvolutionalNeuralNetwork/ F. Liang Cambridge MLG RCC 5 Nov, 2015 23 / 39
  • 24. Dynamic pooling of the similarity matrix Dynamically partition rows and columns of S into np equal parts Min. pool (why?) over each part Normalize µ = 0, σ = 1 and pass on to classifier F. Liang Cambridge MLG RCC 5 Nov, 2015 24 / 39
  • 25. Results F. Liang Cambridge MLG RCC 5 Nov, 2015 25 / 39
  • 26. Qualitative evaluation of unsupervised feature learning Dataset 150,000 sentences from NYT and AP sections of Gigaword corpus for RAE training Setup R100 off-the-shelf feature vectors for word embeddings11 Stanford parser12 to extract parse tree Baseline Recursive average of all word vectors in parse tree 11 Turian, ACL 2010 12 Klein, ACL 2003 F. Liang Cambridge MLG RCC 5 Nov, 2015 26 / 39
  • 27. Nearest Spooled neighbor Figure: Nearest 2-norm neighbor F. Liang Cambridge MLG RCC 5 Nov, 2015 27 / 39
  • 28. Recursive decoding Figure: Unfolding RAE encode/decode F. Liang Cambridge MLG RCC 5 Nov, 2015 28 / 39
  • 29. Paraphrase detection task Dataset Microsoft Research paraphrase corpus (MSRP)13 5,801 sentence pairs, 3,900 labeled as paraphrases 13 Dolan, COLING 2004 F. Liang Cambridge MLG RCC 5 Nov, 2015 29 / 39
  • 30. Paraphrase detection task Setup 4,076 training pairs (67.5% positive), 1,725 test pairs (66.5% positive) ∀(S1, S2) ∈ D, (S2, S1) also added Add features ∈ {0, 1} to Spooled related to the set of numbers in S1 and S2 Numbers in S1 = numbers in S2 (Numbers in S1 ∪ numbers in S2) = ∅ Numbers in one sentence ⊂ numbers in other Softmax classifier over Spooled F. Liang Cambridge MLG RCC 5 Nov, 2015 30 / 39
  • 31. Example results F. Liang Cambridge MLG RCC 5 Nov, 2015 31 / 39
  • 32. Numerical results Recursive averaging: 75.9% Standard RAE: 75.5% Unfolding RAE: 76.8% F. Liang Cambridge MLG RCC 5 Nov, 2015 32 / 39
  • 33. State of the art “Paraphrase Identification (State of the Art).” ACLWiki. Web. 2 Nov 2015. F. Liang Cambridge MLG RCC 5 Nov, 2015 33 / 39
  • 34. Does the dynamic pooling layer add anything? S-histogram 73.0% Only added number features 73.2% Only Spooled 72.6% Top URAE Node 74.2% Spooled + number features 76.8% Is anything suspicious about these results? F. Liang Cambridge MLG RCC 5 Nov, 2015 34 / 39
  • 35. Follow-Up Work Since 2011 F. Liang Cambridge MLG RCC 5 Nov, 2015 35 / 39
  • 36. Extending RAEs to capture compositionality Recursive Matrix-Vector Spaces15 p = f We c1 c2 + b → p = f We Ba + b0 Ab + a0 + p0 15 Socher, EMNLP 2012 F. Liang Cambridge MLG RCC 5 Nov, 2015 36 / 39
  • 37. Encoding the parse tree using LSTMs Tree-Structured LSTMs16 x1 x2 x3 x4 y1 y2 y3 y4 x1 x2 x4 x5 x6 y1 y2 y3 y4 y6 16 Tai, ACL 2015 F. Liang Cambridge MLG RCC 5 Nov, 2015 37 / 39
  • 38. Different “semantic norms” on the word vector space Neural Tensor Networks17 g(e1, R, e2) = uT R f eT 1 W [1:k] R e2 + VR e1 e2 + bR Francesco Guicciardini historian male ItalyFlorence Francesco Patrizi Matteo Rosselli profession gender place of birth nationality location nationality nationality gender 17 Socher, NIPS 2013 F. Liang Cambridge MLG RCC 5 Nov, 2015 38 / 39