Discriminative Training
|
|
- Egbert O’Brien’
- 6 years ago
- Views:
Transcription
1 Discriminative Training February 19, 2013
2 Noisy Channels Again p(e) source English
3 Noisy Channels Again p(e) p(g e) source English German
4 Noisy Channels Again p(e) p(g e) source English German decoder e = arg max e p(e g) = arg max e p(g e) p(g) p(e) = arg max e p(g e) p(e)
5 Noisy Channels Again e = arg max e = arg max e = arg max e p(e g) p(g e) p(g) p(g e) p(e) p(e)
6 Noisy Channels Again e = arg max e = arg max e = arg max e p(e g) p(g e) p(g) p(g e) p(e) p(e) = arg max e = arg max e log p(g e) + log p(e) apple > apple 1 log p(g e) 1 log p(e) {z } {z } w > h(g,e)
7 Noisy Channels Again e = arg max e = arg max e = arg max e p(e g) p(g e) p(g) p(g e) p(e) p(e) = arg max e = arg max e log p(g e) + log p(e) apple > apple 1 log p(g e) 1 log p(e) {z } {z } w > h(g,e)
8 Noisy Channels Again e = arg max e = arg max e p(e g) p(g e) p(g) p(e) = arg max p(g e) p(e) e Does this = arglook max log p(g familiar? e) + log p(e) e = arg max e apple > apple 1 log p(g e) 1 log p(e) {z } {z } w > h(g,e)
9 The Noisy Channel -log p(g e) -log p(e)
10 As a Linear Model -log p(g e) ~w -log p(e)
11 As a Linear Model -log p(g e) ~w -log p(e)
12 As a Linear Model -log p(g e) ~w -log p(e)
13 As a Linear Model -log p(g e) Improvement 1: change ~w to find better ~w translations g -log p(e)
14 As a Linear Model -log p(g e) ~w -log p(e)
15 As a Linear Model -log p(g e) ~w -log p(e)
16 As a Linear Model -log p(g e) ~w -log p(e)
17 As a Linear Model -log p(g e) Improvement 2: Add dimensions to make points separable ~w -log p(e)
18 Linear Models e = arg max e w > h(g, e) Improve the modeling capacity of the noisy channel in two ways Reorient the weight vector Add new dimensions (new features) Questions What features? h(g, e) How do we set the weights? w
19 Mann beißt Hund 18
20 Mann beißt Hund x BITES y 18
21 Mann beißt Hund x BITES y Mann beißt Hund man bites cat Mann beißt Hund dog man chase Mann beißt Hund man bite cat Mann beißt Hund man bite dog Mann beißt Hund dog bites man Mann beißt Hund man bites dog 19
22 Mann beißt Hund x BITES y Mann beißt Hund man bites cat Mann beißt Hund dog man chase Mann beißt Hund man bite cat Mann beißt Hund man bite dog Mann beißt Hund dog bites man Mann beißt Hund man bites dog 19
23 Mann beißt Hund x BITES y Mann beißt Hund man bites cat Mann beißt Hund dog man chase Mann beißt Hund man bite cat Mann beißt Hund man bite dog Mann beißt Hund dog bites man Mann beißt Hund man bites dog 19
24 Mann beißt Hund x BITES y Mann beißt Hund man bites cat Mann beißt Hund dog man chase Mann beißt Hund man bite cat Mann beißt Hund man bite dog Mann beißt Hund dog bites man Mann beißt Hund man bites dog 19
25 Mann beißt Hund x BITES y Mann beißt Hund man bites cat Mann beißt Hund dog man chase Mann beißt Hund man bite cat Mann beißt Hund man bite dog Mann beißt Hund dog bites man Mann beißt Hund man bites dog 19
26 Feature Classes Lexical Are lexical choices appropriate? bank = River bank vs. Financial institution 20
27 Feature Classes Lexical Are lexical choices appropriate? bank = River bank vs. Financial institution Configurational Are semantic/syntactic relations preserved? Dog bites man vs. Man bites dog 20
28 Feature Classes Lexical Are lexical choices appropriate? bank = River bank vs. Financial institution Configurational Are semantic/syntactic relations preserved? Dog bites man vs. Man bites dog Grammatical Is the output fluent / well-formed? Man bites dog vs. Man bite dog 20
29 What do lexical features look like? Mann beißt Hund man bites cat 21
30 What do lexical features look like? Mann beißt Hund man bites cat 21
31 What do lexical features look like? Mann beißt Hund man bites cat First attempt: score(g, e) =w > h(g, e) ( 1, 9i, j : g i = Hund,e j = cat h 15,342 (g, e) = 0, otherwise 21
32 What do lexical features look like? Mann beißt Hund man bites cat First attempt: score(g, e) =w > h(g, e) ( 1, 9i, j : g i = Hund,e j = cat h 15,342 (g, e) = 0, otherwise But what if a cat is being chased by a Hund? 21
33 What do lexical features look like? Mann beißt Hund man bites cat Latent variables enable more precise features: score(g, e, a) =w > h(g, e, a) X ( 1, if g i = Hund,e j = cat h 15,342 (g, e, a) = 0, otherwise (i,j)2a 22
34 Standard Features Target side features log p(e) [ n-gram language model ] Number of words in hypothesis Non-English character count Source + target features log relative frequency e f of each rule [ log #(e,f) - log #(f) ] log relative frequency f e of each rule [ log #(e,f) - log #(e) ] lexical translation log probability e f of each rule [ log pmodel1(e f) ] lexical translation log probability f e of each rule [ log pmodel1(f e) ] Other features Count of rules/phrases used Reordering pattern probabilities 23
35 Parameter Learning 24
36 Hypothesis Space h 1 h 2 25
37 Hypothesis Space h 1 Hypotheses h 2 25
38 Hypothesis Space h 1 References h 2 26
39 Preliminaries We assume a decoder that computes: he, a i = arg max he,ai w> h(g, e, a) And K-best lists of, that is: { e i, a i } i=k i=1 = arg i th - max he,ai w> h(g, e, a) Standard, efficient algorithms exist for this. 27
40 Learning Weights Try to match the reference translation exactly Conditional random field Maximize the conditional probability of the reference translations Average over the different latent variables Max-margin Find the weight vector that separates the reference translation from others by the maximal margin Maximal setting of the latent variables 28
41 Learning Weights Try to match the reference translation exactly Conditional random field Maximize the conditional probability of the reference translations Average over the different latent variables Max-margin Find the weight vector that separates the reference translation from others by the maximal margin Maximal setting of the latent variables 28
42 Problems These methods give full credit when the model exactly produces the reference and no credit otherwise What is the problem with this? There are many ways to translate a sentence What if we have multiple reference translations? What about partial credit? 29
43 Problems These methods give full credit when the model exactly produces the reference and no credit otherwise What is the problem with this? There are many ways to translate a sentence What if we have multiple reference translations? What about partial credit? 29
44 Cost-Sensitive Training Assume we have a cost function that gives a score for how good/bad a translation is (ê, E) [0, 1] Optimize the weight vector by making reference to this function We will talk about two ways to do this 30
45 K-Best List Example h 1 ~w h 2 31
46 K-Best List Example h 1 ~w #8 #7 #3 #6 #5 #4 #2#1 #10 #9 h 2 31
47 K-Best List Example h 1 ~w #3 #6 #5 #4 #2#1 0.8 apple < apple < apple < 0.6 #8 #7 0.2 apple < apple < 0.2 #10 #9 h 2 32
48 Training as Classification Pairwise Ranking Optimization Reduce training problem to binary classification with a linear model Algorithm For i=1 to N Pick random pair of hypotheses (A,B) from K-best list Use cost function to determine if is A or B better Create ith training instance Train binary linear classifier 33
49 h 1 #6 #3 #2 #1 0.8 apple < apple < 0.8 #5 #4 0.4 apple < 0.6 #8 #7 0.2 apple < apple < 0.2 #10 #9 h 2 h 1 h 2 34
50 h 1 #6 #3 #2 #1 0.8 apple < apple < 0.8 #5 #4 0.4 apple < 0.6 #8 #7 0.2 apple < apple < 0.2 #10 #9 h 2 h 1 h 2 34
51 h 1 #6 #3 #2 #1 Worse! 0.8 apple < apple < 0.8 #5 #4 0.4 apple < 0.6 #8 #7 0.2 apple < apple < 0.2 #10 #9 h 2 h 1 h 2 35
52 h 1 #6 #3 #2 #1 Worse! 0.8 apple < apple < 0.8 #5 #4 0.4 apple < 0.6 #8 #7 0.2 apple < apple < 0.2 #10 #9 h 2 h 1 h 2 36
53 h 1 #6 #3 #2 #1 0.8 apple < apple < 0.8 #5 #4 0.4 apple < 0.6 #8 #7 0.2 apple < apple < 0.2 #10 #9 h 2 h 1 h 2 37
54 h 1 #6 #3 #2 #1 0.8 apple < apple < 0.8 #5 #4 0.4 apple < 0.6 #8 #7 Better! 0.2 apple < apple < 0.2 #10 #9 h 2 h 1 h 2 38
55 h 1 #6 #3 #2 #1 0.8 apple < apple < 0.8 #5 #4 0.4 apple < 0.6 #8 #7 Better! 0.2 apple < apple < 0.2 #10 #9 h 2 h 1 h 2 39
56 h 1 #6 #3 #2 #1 Worse! 0.8 apple < apple < 0.8 #5 #4 0.4 apple < 0.6 #8 #7 0.2 apple < apple < 0.2 #10 #9 h 2 h 1 h 2 40
57 h 1 #6 #3 #2 #1 0.8 apple < apple < 0.8 #5 #4 0.4 apple < 0.6 #8 #7 0.2 apple < apple < 0.2 Better! #10 #9 h 2 h 1 h 2 41
58 h 1 #6 #3 #2 #1 0.8 apple < apple < 0.8 #5 #4 0.4 apple < 0.6 #8 #7 0.2 apple < apple < 0.2 #10 #9 h 2 h 1 h 2 42
59 h 1 h 2 Fit a linear model 43
60 h 1 h 2 ~w Fit a linear model 44
61 K-Best List Example h 1 #3 #2#1 0.8 apple < 1.0 #6 #5 #4 0.6 apple < apple < 0.6 ~w #8 #7 0.2 apple < apple < 0.2 #10 #9 h 2 45
62 MERT Minimum Error Rate Training Directly target an automatic evaluation metric BLEU is defined at the corpus level MERT optimizes at the corpus level Downsides Does not deal well with > ~20 features 46
63 MERT Given weight vector w, any hypothesis he, ai will have a (scalar) score m = w > h(g, e, a) Now pick a search vector v, and consider how the score of this hypothesis will change: w new = w + v m =(w + v) > h(g, e, a) = w > h(g, e, a) {z } b + v > h(g, e, a) {z } a m = a + b 47
64 MERT Given weight vector w, any hypothesis he, ai will have a (scalar) score m = w > h(g, e, a) Now pick a search vector v, and consider how the score of this hypothesis will change: w new = w + v m =(w + v) > h(g, e, a) = w > h(g, e, a) {z } b + v > h(g, e, a) {z } a m = a + b 48
65 MERT Given weight vector w, any hypothesis he, ai will have a (scalar) score m = w > h(g, e, a) Now pick a search vector v, and consider how the score of this hypothesis will change: w new = w + v m =(w + v) > h(g, e, a) = w > h(g, e, a) {z } b + v > h(g, e, a) {z } a m = a + b 49
66 MERT Given weight vector w, any hypothesis he, ai will have a (scalar) score m = w > h(g, e, a) Now pick a search vector v, and consider how the score of this hypothesis will change: w new = w + v m =(w + v) > h(g, e, a) = w > h(g, e, a) {z } b + v > h(g, e, a) {z } a m = a + b 50
67 MERT Given weight vector w, any hypothesis he, ai will have a (scalar) score m = w > h(g, e, a) Now pick a search vector v, and consider how the score of this hypothesis will change: w new = w + v m =(w + v) > h(g, e, a) = w > h(g, e, a) {z } b + v > h(g, e, a) {z } a m = a + b 51
68 Given weight vector MERT w will have a (scalar) score, any hypothesis he, ai m = w > h(g, e, a) Now pick a search vector v, and consider how the score of this hypothesis will change: w new = w + v m =(w + v) > h(g, e, a) = w > h(g, e, a) {z } b = a + b + v > h(g, e, a) {z } a m Linear function in 2D! 51
69 MERT m 52
70 MERT m Recall our k-best set { e i, a i } K i=1 53
71 MERT m Recall our k-best set { e i, a i } K i=1 54
72 MERT m 55
73 MERT he 162, a 162i m he 28, a 28i he 73, a 73i 56
74 MERT he 162, a 162i m he 28, a 28i he 73, a 73i 57
75 MERT he 162, a 162i m he 28, a 28i he 73, a 73i errors 58
76 MERT he 162, a 162i m he 28, a 28i he 73, a 73i errors 59
77 MERT m errors 60
78 MERT m errors 61
79 errors Let w new = v + w 62
80 MERT In practice errors are sufficient statistics for evaluation metrics (e.g., BLEU) Can maximize or minimize! Envelope can also be computed using dynamic programming Interesting complexity bounds How do you pick the search direction? 63
81 Summary Evaluation metrics Figure out how well we re doing Figure out if a feature helps But ALSO: train your system! What s a great way to improve translation? Improve evaluation! 64
82 Thank You! m he 162, a 162i he 28, a 28i he 73, a 73i 65
Discriminative Training. March 4, 2014
Discriminative Training March 4, 2014 Noisy Channels Again p(e) source English Noisy Channels Again p(e) p(g e) source English German Noisy Channels Again p(e) p(g e) source English German decoder e =
More informationDecoding Revisited: Easy-Part-First & MERT. February 26, 2015
Decoding Revisited: Easy-Part-First & MERT February 26, 2015 Translating the Easy Part First? the tourism initiative addresses this for the first time the die tm:-0.19,lm:-0.4, d:0, all:-0.65 tourism touristische
More informationThe Geometry of Statistical Machine Translation
The Geometry of Statistical Machine Translation Presented by Rory Waite 16th of December 2015 ntroduction Linear Models Convex Geometry The Minkowski Sum Projected MERT Conclusions ntroduction We provide
More informationTuning as Linear Regression
Tuning as Linear Regression Marzieh Bazrafshan, Tagyoung Chung and Daniel Gildea Department of Computer Science University of Rochester Rochester, NY 14627 Abstract We propose a tuning method for statistical
More informationCross-Lingual Language Modeling for Automatic Speech Recogntion
GBO Presentation Cross-Lingual Language Modeling for Automatic Speech Recogntion November 14, 2003 Woosung Kim woosung@cs.jhu.edu Center for Language and Speech Processing Dept. of Computer Science The
More informationAlgorithms for NLP. Machine Translation II. Taylor Berg-Kirkpatrick CMU Slides: Dan Klein UC Berkeley
Algorithms for NLP Machine Translation II Taylor Berg-Kirkpatrick CMU Slides: Dan Klein UC Berkeley Announcements Project 4: Word Alignment! Will be released soon! (~Monday) Phrase-Based System Overview
More informationWord Alignment. Chris Dyer, Carnegie Mellon University
Word Alignment Chris Dyer, Carnegie Mellon University John ate an apple John hat einen Apfel gegessen John ate an apple John hat einen Apfel gegessen Outline Modeling translation with probabilistic models
More informationLearning to translate with neural networks. Michael Auli
Learning to translate with neural networks Michael Auli 1 Neural networks for text processing Similar words near each other France Spain dog cat Neural networks for text processing Similar words near each
More informationNatural Language Processing. Classification. Features. Some Definitions. Classification. Feature Vectors. Classification I. Dan Klein UC Berkeley
Natural Language Processing Classification Classification I Dan Klein UC Berkeley Classification Automatically make a decision about inputs Example: document category Example: image of digit digit Example:
More informationMIRA, SVM, k-nn. Lirong Xia
MIRA, SVM, k-nn Lirong Xia Linear Classifiers (perceptrons) Inputs are feature values Each feature has a weight Sum is the activation activation w If the activation is: Positive: output +1 Negative, output
More informationMachine Translation. CL1: Jordan Boyd-Graber. University of Maryland. November 11, 2013
Machine Translation CL1: Jordan Boyd-Graber University of Maryland November 11, 2013 Adapted from material by Philipp Koehn CL1: Jordan Boyd-Graber (UMD) Machine Translation November 11, 2013 1 / 48 Roadmap
More informationCRF Word Alignment & Noisy Channel Translation
CRF Word Alignment & Noisy Channel Translation January 31, 2013 Last Time... X p( Translation)= p(, Translation) Alignment Alignment Last Time... X p( Translation)= p(, Translation) Alignment X Alignment
More informationA Syntax-based Statistical Machine Translation Model. Alexander Friedl, Georg Teichtmeister
A Syntax-based Statistical Machine Translation Model Alexander Friedl, Georg Teichtmeister 4.12.2006 Introduction The model Experiment Conclusion Statistical Translation Model (STM): - mathematical model
More informationMassachusetts Institute of Technology
Massachusetts Institute of Technology 6.867 Machine Learning, Fall 2006 Problem Set 5 Due Date: Thursday, Nov 30, 12:00 noon You may submit your solutions in class or in the box. 1. Wilhelm and Klaus are
More informationMachine Translation Evaluation
Machine Translation Evaluation Sara Stymne 2017-03-29 Partly based on Philipp Koehn s slides for chapter 8 Why Evaluation? How good is a given machine translation system? Which one is the best system for
More informationPhrase-Based Statistical Machine Translation with Pivot Languages
Phrase-Based Statistical Machine Translation with Pivot Languages N. Bertoldi, M. Barbaiani, M. Federico, R. Cattoni FBK, Trento - Italy Rovira i Virgili University, Tarragona - Spain October 21st, 2008
More informationEvaluation. Brian Thompson slides by Philipp Koehn. 25 September 2018
Evaluation Brian Thompson slides by Philipp Koehn 25 September 2018 Evaluation 1 How good is a given machine translation system? Hard problem, since many different translations acceptable semantic equivalence
More informationACS Introduction to NLP Lecture 2: Part of Speech (POS) Tagging
ACS Introduction to NLP Lecture 2: Part of Speech (POS) Tagging Stephen Clark Natural Language and Information Processing (NLIP) Group sc609@cam.ac.uk The POS Tagging Problem 2 England NNP s POS fencers
More informationIBM Model 1 for Machine Translation
IBM Model 1 for Machine Translation Micha Elsner March 28, 2014 2 Machine translation A key area of computational linguistics Bar-Hillel points out that human-like translation requires understanding of
More informationLab 12: Structured Prediction
December 4, 2014 Lecture plan structured perceptron application: confused messages application: dependency parsing structured SVM Class review: from modelization to classification What does learning mean?
More informationMidterm sample questions
Midterm sample questions CS 585, Brendan O Connor and David Belanger October 12, 2014 1 Topics on the midterm Language concepts Translation issues: word order, multiword translations Human evaluation Parts
More informationINF5820/INF9820 LANGUAGE TECHNOLOGICAL APPLICATIONS. Jan Tore Lønning, Lecture 3, 7 Sep., 2016
1 INF5820/INF9820 LANGUAGE TECHNOLOGICAL APPLICATIONS Jan Tore Lønning, Lecture 3, 7 Sep., 2016 jtl@ifi.uio.no Machine Translation Evaluation 2 1. Automatic MT-evaluation: 1. BLEU 2. Alternatives 3. Evaluation
More informationMinimum Error Rate Training Semiring
Minimum Error Rate Training Semiring Artem Sokolov & François Yvon LIMSI-CNRS & LIMSI-CNRS/Univ. Paris Sud {artem.sokolov,francois.yvon}@limsi.fr EAMT 2011 31 May 2011 Artem Sokolov & François Yvon (LIMSI)
More informationQuasi-Synchronous Phrase Dependency Grammars for Machine Translation. lti
Quasi-Synchronous Phrase Dependency Grammars for Machine Translation Kevin Gimpel Noah A. Smith 1 Introduction MT using dependency grammars on phrases Phrases capture local reordering and idiomatic translations
More informationNatural Language Processing (CSEP 517): Machine Translation
Natural Language Processing (CSEP 57): Machine Translation Noah Smith c 207 University of Washington nasmith@cs.washington.edu May 5, 207 / 59 To-Do List Online quiz: due Sunday (Jurafsky and Martin, 2008,
More informationGoogle s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Google s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation Y. Wu, M. Schuster, Z. Chen, Q.V. Le, M. Norouzi, et al. Google arxiv:1609.08144v2 Reviewed by : Bill
More informationA Discriminative Model for Semantics-to-String Translation
A Discriminative Model for Semantics-to-String Translation Aleš Tamchyna 1 and Chris Quirk 2 and Michel Galley 2 1 Charles University in Prague 2 Microsoft Research July 30, 2015 Tamchyna, Quirk, Galley
More informationClass 4: Classification. Quaid Morris February 11 th, 2011 ML4Bio
Class 4: Classification Quaid Morris February 11 th, 211 ML4Bio Overview Basic concepts in classification: overfitting, cross-validation, evaluation. Linear Discriminant Analysis and Quadratic Discriminant
More informationConditional Language Modeling. Chris Dyer
Conditional Language Modeling Chris Dyer Unconditional LMs A language model assigns probabilities to sequences of words,. w =(w 1,w 2,...,w`) It is convenient to decompose this probability using the chain
More informationCS 188: Artificial Intelligence. Outline
CS 188: Artificial Intelligence Lecture 21: Perceptrons Pieter Abbeel UC Berkeley Many slides adapted from Dan Klein. Outline Generative vs. Discriminative Binary Linear Classifiers Perceptron Multi-class
More informationCOMS 4705 (Fall 2011) Machine Translation Part II
COMS 4705 (Fall 2011) Machine Translation Part II 1 Recap: The Noisy Channel Model Goal: translation system from French to English Have a model p(e f) which estimates conditional probability of any English
More informationA Pairwise Document Analysis Approach for Monolingual Plagiarism Detection
A Pairwise Document Analysis Approach for Monolingual Plagiarism Detection Introuction Plagiarism: Unauthorize use of Text, coe, iea, Plagiarism etection research area has receive increasing attention
More informationWord Alignment III: Fertility Models & CRFs. February 3, 2015
Word Alignment III: Fertility Models & CRFs February 3, 2015 Last Time... X p( Translation)= p(, Translation) Alignment = X Alignment Alignment p( p( Alignment) Translation Alignment) {z } {z } X z } {
More informationFrom perceptrons to word embeddings. Simon Šuster University of Groningen
From perceptrons to word embeddings Simon Šuster University of Groningen Outline A basic computational unit Weighting some input to produce an output: classification Perceptron Classify tweets Written
More information1 Evaluation of SMT systems: BLEU
1 Evaluation of SMT systems: BLEU Idea: We want to define a repeatable evaluation method that uses: a gold standard of human generated reference translations a numerical translation closeness metric in
More informationLinear models: the perceptron and closest centroid algorithms. D = {(x i,y i )} n i=1. x i 2 R d 9/3/13. Preliminaries. Chapter 1, 7.
Preliminaries Linear models: the perceptron and closest centroid algorithms Chapter 1, 7 Definition: The Euclidean dot product beteen to vectors is the expression d T x = i x i The dot product is also
More informationCS 188: Artificial Intelligence Spring Announcements
CS 188: Artificial Intelligence Spring 2010 Lecture 22: Nearest Neighbors, Kernels 4/18/2011 Pieter Abbeel UC Berkeley Slides adapted from Dan Klein Announcements On-going: contest (optional and FUN!)
More informationNaïve Bayes, Maxent and Neural Models
Naïve Bayes, Maxent and Neural Models CMSC 473/673 UMBC Some slides adapted from 3SLP Outline Recap: classification (MAP vs. noisy channel) & evaluation Naïve Bayes (NB) classification Terminology: bag-of-words
More informationIntroduction to Signal Detection and Classification. Phani Chavali
Introduction to Signal Detection and Classification Phani Chavali Outline Detection Problem Performance Measures Receiver Operating Characteristics (ROC) F-Test - Test Linear Discriminant Analysis (LDA)
More informationSparse vectors recap. ANLP Lecture 22 Lexical Semantics with Dense Vectors. Before density, another approach to normalisation.
ANLP Lecture 22 Lexical Semantics with Dense Vectors Henry S. Thompson Based on slides by Jurafsky & Martin, some via Dorota Glowacka 5 November 2018 Previous lectures: Sparse vectors recap How to represent
More informationANLP Lecture 22 Lexical Semantics with Dense Vectors
ANLP Lecture 22 Lexical Semantics with Dense Vectors Henry S. Thompson Based on slides by Jurafsky & Martin, some via Dorota Glowacka 5 November 2018 Henry S. Thompson ANLP Lecture 22 5 November 2018 Previous
More informationDeep Learning Basics Lecture 10: Neural Language Models. Princeton University COS 495 Instructor: Yingyu Liang
Deep Learning Basics Lecture 10: Neural Language Models Princeton University COS 495 Instructor: Yingyu Liang Natural language Processing (NLP) The processing of the human languages by computers One of
More informationMachine Translation 1 CS 287
Machine Translation 1 CS 287 Review: Conditional Random Field (Lafferty et al, 2001) Model consists of unnormalized weights log ŷ(c i 1 ) ci = feat(x, c i 1 )W + b Out of log space, ŷ(c i 1 ) ci = exp(feat(x,
More informationMulticlass and Introduction to Structured Prediction
Multiclass and Introduction to Structured Prediction David S. Rosenberg New York University March 27, 2018 David S. Rosenberg (New York University) DS-GA 1003 / CSCI-GA 2567 March 27, 2018 1 / 49 Contents
More informationWarm up: risk prediction with logistic regression
Warm up: risk prediction with logistic regression Boss gives you a bunch of data on loans defaulting or not: {(x i,y i )} n i= x i 2 R d, y i 2 {, } You model the data as: P (Y = y x, w) = + exp( yw T
More informationMulticlass and Introduction to Structured Prediction
Multiclass and Introduction to Structured Prediction David S. Rosenberg Bloomberg ML EDU November 28, 2017 David S. Rosenberg (Bloomberg ML EDU) ML 101 November 28, 2017 1 / 48 Introduction David S. Rosenberg
More informationLogistic Regression. Machine Learning Fall 2018
Logistic Regression Machine Learning Fall 2018 1 Where are e? We have seen the folloing ideas Linear models Learning as loss minimization Bayesian learning criteria (MAP and MLE estimation) The Naïve Bayes
More informationMachine Learning for NLP
Machine Learning for NLP Uppsala University Department of Linguistics and Philology Slides borrowed from Ryan McDonald, Google Research Machine Learning for NLP 1(50) Introduction Linear Classifiers Classifiers
More informationLECTURER: BURCU CAN Spring
LECTURER: BURCU CAN 2017-2018 Spring Regular Language Hidden Markov Model (HMM) Context Free Language Context Sensitive Language Probabilistic Context Free Grammar (PCFG) Unrestricted Language PCFGs can
More informationMulticlass Classification
Multiclass Classification David Rosenberg New York University March 7, 2017 David Rosenberg (New York University) DS-GA 1003 March 7, 2017 1 / 52 Introduction Introduction David Rosenberg (New York University)
More informationAnnouncements. CS 188: Artificial Intelligence Spring Classification. Today. Classification overview. Case-Based Reasoning
CS 188: Artificial Intelligence Spring 21 Lecture 22: Nearest Neighbors, Kernels 4/18/211 Pieter Abbeel UC Berkeley Slides adapted from Dan Klein Announcements On-going: contest (optional and FUN!) Remaining
More informationMulti-Label Informed Latent Semantic Indexing
Multi-Label Informed Latent Semantic Indexing Shipeng Yu 12 Joint work with Kai Yu 1 and Volker Tresp 1 August 2005 1 Siemens Corporate Technology Department of Neural Computation 2 University of Munich
More informationCS 188: Artificial Intelligence Spring Announcements
CS 188: Artificial Intelligence Spring 2010 Lecture 24: Perceptrons and More! 4/22/2010 Pieter Abbeel UC Berkeley Slides adapted from Dan Klein Announcements W7 due tonight [this is your last written for
More informationChapter 3: Basics of Language Modeling
Chapter 3: Basics of Language Modeling Section 3.1. Language Modeling in Automatic Speech Recognition (ASR) All graphs in this section are from the book by Schukat-Talamazzini unless indicated otherwise
More informationstatistical machine translation
statistical machine translation P A R T 3 : D E C O D I N G & E V A L U A T I O N CSC401/2511 Natural Language Computing Spring 2019 Lecture 6 Frank Rudzicz and Chloé Pou-Prom 1 University of Toronto Statistical
More informationTALP Phrase-Based System and TALP System Combination for the IWSLT 2006 IWSLT 2006, Kyoto
TALP Phrase-Based System and TALP System Combination for the IWSLT 2006 IWSLT 2006, Kyoto Marta R. Costa-jussà, Josep M. Crego, Adrià de Gispert, Patrik Lambert, Maxim Khalilov, José A.R. Fonollosa, José
More informationCPSC 340: Machine Learning and Data Mining
CPSC 340: Machine Learning and Data Mining Linear Classifiers: multi-class Original version of these slides by Mark Schmidt, with modifications by Mike Gelbart. 1 Admin Assignment 4: Due in a week Midterm:
More informationDeep Learning Sequence to Sequence models: Attention Models. 17 March 2018
Deep Learning Sequence to Sequence models: Attention Models 17 March 2018 1 Sequence-to-sequence modelling Problem: E.g. A sequence X 1 X N goes in A different sequence Y 1 Y M comes out Speech recognition:
More informationChapter 3: Basics of Language Modelling
Chapter 3: Basics of Language Modelling Motivation Language Models are used in Speech Recognition Machine Translation Natural Language Generation Query completion For research and development: need a simple
More informationAutomatic Speech Recognition and Statistical Machine Translation under Uncertainty
Outlines Automatic Speech Recognition and Statistical Machine Translation under Uncertainty Lambert Mathias Advisor: Prof. William Byrne Thesis Committee: Prof. Gerard Meyer, Prof. Trac Tran and Prof.
More informationExploitation of Machine Learning Techniques in Modelling Phrase Movements for Machine Translation
Journal of Machine Learning Research 12 (2011) 1-30 Submitted 5/10; Revised 11/10; Published 1/11 Exploitation of Machine Learning Techniques in Modelling Phrase Movements for Machine Translation Yizhao
More informationProbabilistic Context-Free Grammar
Probabilistic Context-Free Grammar Petr Horáček, Eva Zámečníková and Ivana Burgetová Department of Information Systems Faculty of Information Technology Brno University of Technology Božetěchova 2, 612
More informationClassification Logistic Regression
Announcements: Classification Logistic Regression Machine Learning CSE546 Sham Kakade University of Washington HW due on Friday. Today: Review: sub-gradients,lasso Logistic Regression October 3, 26 Sham
More informationLinear Classifiers IV
Universität Potsdam Institut für Informatik Lehrstuhl Linear Classifiers IV Blaine Nelson, Tobias Scheffer Contents Classification Problem Bayesian Classifier Decision Linear Classifiers, MAP Models Logistic
More informationLearning Linear Detectors
Learning Linear Detectors Instructor - Simon Lucey 16-423 - Designing Computer Vision Apps Today Detection versus Classification Bayes Classifiers Linear Classifiers Examples of Detection 3 Learning: Detection
More informationName: Student number:
UNIVERSITY OF TORONTO Faculty of Arts and Science APRIL 2018 EXAMINATIONS CSC321H1S Duration 3 hours No Aids Allowed Name: Student number: This is a closed-book test. It is marked out of 35 marks. Please
More informationCMU-Q Lecture 24:
CMU-Q 15-381 Lecture 24: Supervised Learning 2 Teacher: Gianni A. Di Caro SUPERVISED LEARNING Hypotheses space Hypothesis function Labeled Given Errors Performance criteria Given a collection of input
More informationEXAM IN STATISTICAL MACHINE LEARNING STATISTISK MASKININLÄRNING
EXAM IN STATISTICAL MACHINE LEARNING STATISTISK MASKININLÄRNING DATE AND TIME: June 9, 2018, 09.00 14.00 RESPONSIBLE TEACHER: Andreas Svensson NUMBER OF PROBLEMS: 5 AIDING MATERIAL: Calculator, mathematical
More informationCS4705. Probability Review and Naïve Bayes. Slides from Dragomir Radev
CS4705 Probability Review and Naïve Bayes Slides from Dragomir Radev Classification using a Generative Approach Previously on NLP discriminative models P C D here is a line with all the social media posts
More informationThe Noisy Channel Model and Markov Models
1/24 The Noisy Channel Model and Markov Models Mark Johnson September 3, 2014 2/24 The big ideas The story so far: machine learning classifiers learn a function that maps a data item X to a label Y handle
More informationVariational Decoding for Statistical Machine Translation
Variational Decoding for Statistical Machine Translation Zhifei Li, Jason Eisner, and Sanjeev Khudanpur Center for Language and Speech Processing Computer Science Department Johns Hopkins University 1
More informationMulticlass Boosting with Repartitioning
Multiclass Boosting with Repartitioning Ling Li Learning Systems Group, Caltech ICML 2006 Binary and Multiclass Problems Binary classification problems Y = { 1, 1} Multiclass classification problems Y
More informationSpeech Translation: from Singlebest to N-Best to Lattice Translation. Spoken Language Communication Laboratories
Speech Translation: from Singlebest to N-Best to Lattice Translation Ruiqiang ZHANG Genichiro KIKUI Spoken Language Communication Laboratories 2 Speech Translation Structure Single-best only ASR Single-best
More informationNatural Language Processing Prof. Pawan Goyal Department of Computer Science and Engineering Indian Institute of Technology, Kharagpur
Natural Language Processing Prof. Pawan Goyal Department of Computer Science and Engineering Indian Institute of Technology, Kharagpur Lecture - 18 Maximum Entropy Models I Welcome back for the 3rd module
More informationStatistical Ranking Problem
Statistical Ranking Problem Tong Zhang Statistics Department, Rutgers University Ranking Problems Rank a set of items and display to users in corresponding order. Two issues: performance on top and dealing
More informationTopics in Natural Language Processing
Topics in Natural Language Processing Shay Cohen Institute for Language, Cognition and Computation University of Edinburgh Lecture 9 Administrativia Next class will be a summary Please email me questions
More informationVote. Vote on timing for night section: Option 1 (what we have now) Option 2. Lecture, 6:10-7:50 25 minute dinner break Tutorial, 8:15-9
Vote Vote on timing for night section: Option 1 (what we have now) Lecture, 6:10-7:50 25 minute dinner break Tutorial, 8:15-9 Option 2 Lecture, 6:10-7 10 minute break Lecture, 7:10-8 10 minute break Tutorial,
More informationAlgorithms for NLP. Classification II. Taylor Berg-Kirkpatrick CMU Slides: Dan Klein UC Berkeley
Algorithms for NLP Classification II Taylor Berg-Kirkpatrick CMU Slides: Dan Klein UC Berkeley Minimize Training Error? A loss function declares how costly each mistake is E.g. 0 loss for correct label,
More informationLearning Features from Co-occurrences: A Theoretical Analysis
Learning Features from Co-occurrences: A Theoretical Analysis Yanpeng Li IBM T. J. Watson Research Center Yorktown Heights, New York 10598 liyanpeng.lyp@gmail.com Abstract Representing a word by its co-occurrences
More informationDiscriminative part-based models. Many slides based on P. Felzenszwalb
More sliding window detection: ti Discriminative part-based models Many slides based on P. Felzenszwalb Challenge: Generic object detection Pedestrian detection Features: Histograms of oriented gradients
More informationLexical Translation Models 1I. January 27, 2015
Lexical Translation Models 1I January 27, 2015 Last Time... X p( Translation)= p(, Translation) Alignment = X Alignment Alignment p( p( Alignment) Translation Alignment) {z } {z } X z } { z } { p(e f,m)=
More informationApplied Natural Language Processing
Applied Natural Language Processing Info 256 Lecture 7: Testing (Feb 12, 2019) David Bamman, UC Berkeley Significance in NLP You develop a new method for text classification; is it better than what comes
More information6.864 (Fall 2007) Machine Translation Part II
6.864 (Fall 2007) Machine Translation Part II 1 Recap: The Noisy Channel Model Goal: translation system from French to English Have a model P(e f) which estimates conditional probability of any English
More informationImproved Decipherment of Homophonic Ciphers
Improved Decipherment of Homophonic Ciphers Malte Nuhn and Julian Schamper and Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department, RWTH Aachen University, Aachen,
More informationAN ABSTRACT OF THE DISSERTATION OF
AN ABSTRACT OF THE DISSERTATION OF Kai Zhao for the degree of Doctor of Philosophy in Computer Science presented on May 30, 2017. Title: Structured Learning with Latent Variables: Theory and Algorithms
More informationTheory of Alignment Generators and Applications to Statistical Machine Translation
Theory of Alignment Generators and Applications to Statistical Machine Translation Raghavendra Udupa U Hemanta K Mai IBM India Research Laboratory, New Delhi {uraghave, hemantkm}@inibmcom Abstract Viterbi
More informationLearning by constraints and SVMs (2)
Statistical Techniques in Robotics (16-831, F12) Lecture#14 (Wednesday ctober 17) Learning by constraints and SVMs (2) Lecturer: Drew Bagnell Scribe: Albert Wu 1 1 Support Vector Ranking Machine pening
More informationClassification & Information Theory Lecture #8
Classification & Information Theory Lecture #8 Introduction to Natural Language Processing CMPSCI 585, Fall 2007 University of Massachusetts Amherst Andrew McCallum Today s Main Points Automatically categorizing
More informationLexical Translation Models 1I
Lexical Translation Models 1I Machine Translation Lecture 5 Instructor: Chris Callison-Burch TAs: Mitchell Stern, Justin Chiu Website: mt-class.org/penn Last Time... X p( Translation)= p(, Translation)
More informationSupport Vector Machine (SVM) & Kernel CE-717: Machine Learning Sharif University of Technology. M. Soleymani Fall 2012
Support Vector Machine (SVM) & Kernel CE-717: Machine Learning Sharif University of Technology M. Soleymani Fall 2012 Linear classifier Which classifier? x 2 x 1 2 Linear classifier Margin concept x 2
More informationBayesian Methods: Naïve Bayes
Bayesian Methods: aïve Bayes icholas Ruozzi University of Texas at Dallas based on the slides of Vibhav Gogate Last Time Parameter learning Learning the parameter of a simple coin flipping model Prior
More informationwith Local Dependencies
CS11-747 Neural Networks for NLP Structured Prediction with Local Dependencies Xuezhe Ma (Max) Site https://phontron.com/class/nn4nlp2017/ An Example Structured Prediction Problem: Sequence Labeling Sequence
More informationSpectral Unsupervised Parsing with Additive Tree Metrics
Spectral Unsupervised Parsing with Additive Tree Metrics Ankur Parikh, Shay Cohen, Eric P. Xing Carnegie Mellon, University of Edinburgh Ankur Parikh 2014 1 Overview Model: We present a novel approach
More informationStatistical Machine Translation of Natural Languages
1/37 Statistical Machine Translation of Natural Languages Rule Extraction and Training Probabilities Matthias Büchse, Toni Dietze, Johannes Osterholzer, Torsten Stüber, Heiko Vogler Technische Universität
More informationPolyhedral Outer Approximations with Application to Natural Language Parsing
Polyhedral Outer Approximations with Application to Natural Language Parsing André F. T. Martins 1,2 Noah A. Smith 1 Eric P. Xing 1 1 Language Technologies Institute School of Computer Science Carnegie
More informationCS230: Lecture 10 Sequence models II
CS23: Lecture 1 Sequence models II Today s outline We will learn how to: - Automatically score an NLP model I. BLEU score - Improve Machine II. Beam Search Translation results with Beam search III. Speech
More informationFrom Binary to Multiclass Classification. CS 6961: Structured Prediction Spring 2018
From Binary to Multiclass Classification CS 6961: Structured Prediction Spring 2018 1 So far: Binary Classification We have seen linear models Learning algorithms Perceptron SVM Logistic Regression Prediction
More informationDecoding in Statistical Machine Translation. Mid-course Evaluation. Decoding. Christian Hardmeier
Decoding in Statistical Machine Translation Christian Hardmeier 2016-05-04 Mid-course Evaluation http://stp.lingfil.uu.se/~sara/kurser/mt16/ mid-course-eval.html Decoding The decoder is the part of the
More informationLecture 12: Algorithms for HMMs
Lecture 12: Algorithms for HMMs Nathan Schneider (some slides from Sharon Goldwater; thanks to Jonathan May for bug fixes) ENLP 26 February 2018 Recap: tagging POS tagging is a sequence labelling task.
More informationAdvanced Natural Language Processing Syntactic Parsing
Advanced Natural Language Processing Syntactic Parsing Alicia Ageno ageno@cs.upc.edu Universitat Politècnica de Catalunya NLP statistical parsing 1 Parsing Review Statistical Parsing SCFG Inside Algorithm
More information