Lecture 2: Mixing Compositional Semantics and Machine Learning
|
|
- Anne Terry
- 5 years ago
- Views:
Transcription
1 Lecture 2: Mixing Compositional Semantics and Machine Learning Kyle Richardson April 14, 2016
2 Plan main paper: Liang and Potts 2015 (conceptual basis of class) secondary: Mooney 2007 (semantic parsing big ideas), Domingos 2012 (remarks about ML) 2
3 Classical Semantics vs. Statistical Semantics (caricature) Logical Semantics: Logic, algebra, set theory compositional analysis, beyond words, inference, brittle. Statistical Semantics: Optimization, algorithms, geometry distributional analysis, word-based, grounded, shallow. The types of approaches share the long-term vision of achieving deep natural language understanding... 3
4 Montague-style Compositional Semantics Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: John studies. john John (λx.(study x)) studies 4
5 Montague-style Compositional Semantics Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: John studies. john John (λx.(study x)) studies (λx.(study x))(john) (study john ) {True, False} john John (λx.(study x)) studies 4
6 A mini functional interpreter (python) Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: John studies. john John (λx.(study x)) studies >>> students studying = set([ john, mary ]) >>> study = lambda x : x in students studying >>> fun application = lambda fun, val : fun(val) 5
7 A mini functional interpreter (python) Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: John studies. john John (λx.(study x)) studies >>> students studying = set([ john, mary ]) >>> study = lambda x : x in students studying >>> fun application = lambda fun, val : fun(val) >>> fun application(study, bill ) ## What will we get? 5
8 A mini functional interpreter (python) Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: John studies. john John (λx.(study x)) studies >>> students studying = set([ john, mary ]) >>> study = lambda x : x in students studying >>> fun application = lambda fun, val : fun(val) >>> fun application(study, bill ) ## What will we get? >>> False 5
9 A mini functional interpreter (python) Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: John studies. john John (λx.(study x)) studies >>> students studying = set([ john, mary ]) >>> study = lambda x : x in students studying >>> fun application = lambda fun, val : fun(val) >>> fun application(study, mary ) ## What will we get? 6
10 A mini functional interpreter (python) Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: John studies. john John (λx.(study x)) studies >>> students studying = set([ john, mary ]) >>> study = lambda x : x in students studying >>> fun application = lambda fun, val : fun(val) >>> fun application(study, mary ) ## What will we get? >>> True 6
11 Montague-style Compositional Semantics Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: Bill does not study. bill Bill (λx.(study x)) study (λf.λx.(not (f x))) does not 7
12 Montague-style Compositional Semantics Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: Bill does not study. bill Bill (λx.(study x)) study (λf.λx.(not (f x))) does not (λx.(not (study x)))(bill) bill (λx.(not (study x))) Bill (λf.λx.(not (f x))) does not (λx.(study x)) study 7
13 A mini functional interpreter (python) Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: Bill does not study. bill Bill (λx.(study x)) study (λf.λx.(not (f x))) does not >>> students studying = set([ john, mary ]) >>> study = lambda x : x in students studying >>> fun application = lambda fun, val : fun(val) >>> neg = lambda F : (lambda x : not F(x)) 8
14 A mini functional interpreter (python) Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: Bill does not study. bill Bill (λx.(study x)) study (λf.λx.(not (f x))) does not >>> students studying = set([ john, mary ]) >>> study = lambda x : x in students studying >>> fun application = lambda fun, val : fun(val) >>> neg = lambda F : (lambda x : not F(x)) >>> neg(study)( bill ) # True 8
15 A mini functional interpreter (python) Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: Bill does not study. bill Bill (λx.(study x)) study (λf.λx.(not (f x))) does not >>> students studying = set([ john, mary ]) >>> study = lambda x : x in students studying >>> fun application = lambda fun, val : fun(val) >>> neg = lambda F : (lambda x : not F(x)) >>> neg(study)( bill ) # True >>> fun application(neg,study)( bill ) 8
16 A mini functional interpreter (python) Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: Bill does not study. bill Bill (λx.(study x)) study (λf.λx.(not (f x))) does not >>> students studying = set([ john, mary ]) >>> study = lambda x : x in students studying >>> fun application = lambda fun, val : fun(val) >>> neg = lambda F : (lambda x : not F(x)) >>> neg(study)( bill ) # True >>> fun application(neg,study)( bill ) >>> fun application(fun application(neg,study), bill ) 8
17 A mini functional interpreter (python) Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: Bill does not study. bill Bill (λx.(study x)) study (λf.λx.(not (f x))) does not >>> students studying = set([ john, mary ]) >>> study = lambda x : x in students studying >>> fun application = lambda fun, val : fun(val) >>> neg = lambda F : (lambda x : not F(x)) >>> neg(study)( bill ) # True >>> fun application(neg,study)( bill ) >>> fun application(fun application(neg,study), bill ) >>> neg(neg(sleep))( bill ) 8
18 Montague-style Compositional Semantics: What s needed Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: Bill does not study. bill Bill (λx.(study x)) study (λf.λx.(not (f x))) does not Grammar rules for building syntactic structure. Interpretation rules to composing meaning. Decoding algorithm for generating structures 9
19 Montague-style Compositional Semantics: Issues Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: Bill does not study. bill Bill (λx.(study x)) study (λf.λx.(not (f x))) does not Features and (Computational) Issues: compositional, provides a full analysis. supports further inferencing 10
20 Montague-style Compositional Semantics: Issues Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: Bill does not study. bill Bill (λx.(study x)) study (λf.λx.(not (f x))) does not Features and (Computational) Issues: compositional, provides a full analysis. supports further inferencing issue: Does not provide an analysis of words (not grounded). 10
21 Montague-style Compositional Semantics: Issues Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: Bill does not study. bill Bill (λx.(study x)) study (λf.λx.(not (f x))) does not Features and (Computational) Issues: compositional, provides a full analysis. supports further inferencing issue: issue: Does not provide an analysis of words (not grounded). Is brittle, cannot handle uncertainty. 10
22 Montague-style Compositional Semantics: Issues Principle of Compositionality: The meaning of a complex expression is a function of the meaning of its parts and the rules that combine them. Example: Bill does not study. bill Bill (λx.(study x)) study (λf.λx.(not (f x))) does not Features and (Computational) Issues: compositional, provides a full analysis. supports further inferencing issue: issue: issue: Does not provide an analysis of words (not grounded). Is brittle, cannot handle uncertainty. Says nothing about how the translation to logic works. 10
23 Statistical Approaches to Semantics Statistical semantics hypothesis: Statistical patterns of human word usage can be used to figure out what people mean Turney et al. (2010) corpus word-context matrix The furry dog is walking outside... furry walking shiny driving The shiny car is driving... dog A furry cat is walking around... cat A shiny bike is driving... car bike
24 Statistical Approaches to Semantics Statistical semantics hypothesis: Statistical patterns of human word usage can be used to figure out what people mean Turney et al. (2010) corpus word-context matrix furry walking shiny driving dog cat car bike
25 Example Tasks and Applications: Turney et al. (2010) Statistical semantic models are often used in downstream classification or clustering tasks/applications. Term-document matrices Document retrieval/clustering/classification. Question Answering and Retrieval. Essay scoring. Word-Context Matrices Word similarity/clustering/classification Word-sense disambiguation Automatic thesaurus generation/paraphrasing Pair-pair matrices Relational similarity/clustering/classification. Analogy comparison. 13
26 Statistical Approaches to Semantics Statistical semantics hypothesis: Statistical patterns of human word usage can be used to figure out what people mean Turney et al. (2010) corpus word-context matrix The furry dog is walking outside... furry walking shiny driving The shiny car is driving... dog A furry cat is walking around... cat A shiny bike is driving... car bike Features and Issues (caricature): Robust, requires little manual effort, grounded Can provide rich analysis of content words. 14
27 Statistical Approaches to Semantics Statistical semantics hypothesis: Statistical patterns of human word usage can be used to figure out what people mean Turney et al. (2010) corpus word-context matrix The furry dog is walking outside... furry walking shiny driving The shiny car is driving... dog A furry cat is walking around... cat A shiny bike is driving... car bike Features and Issues (caricature): Robust, requires little manual effort, grounded Can provide rich analysis of content words. issue: Hard to scale beyond words. 14
28 Statistical Approaches to Semantics Statistical semantics hypothesis: Statistical patterns of human word usage can be used to figure out what people mean Turney et al. (2010) corpus word-context matrix The furry dog is walking outside... furry walking shiny driving The shiny car is driving... dog A furry cat is walking around... cat A shiny bike is driving... car bike Features and Issues (caricature): Robust, requires little manual effort, grounded Can provide rich analysis of content words. issue: Hard to scale beyond words. issue: In general, hard to model logical operations, shallow. 14
29 Mixing compositional and statistical semantics Desiderata: Want a model of semantics that is robust, reflects real-word usage and learnable, but one that is also compositional. 15
30 Mixing compositional and statistical semantics Desiderata: Want a model of semantics that is robust, reflects real-word usage and learnable, but one that is also compositional. Generalization 15
31 Mixing compositional and statistical semantics Desiderata: Want a model of semantics that is robust, reflects real-word usage and learnable, but one that is also compositional. Generalization Logical semantics: generalize using composition and abstract recursive structures. 15
32 Mixing compositional and statistical semantics Desiderata: Want a model of semantics that is robust, reflects real-word usage and learnable, but one that is also compositional. Generalization Logical semantics: generalize using composition and abstract recursive structures. Machine Learning (classification): learns generalizations through real-world examples (e.g. target input-output) 15
33 Mixing compositional and statistical semantics Desiderata: Want a model of semantics that is robust, reflects real-word usage and learnable, but one that is also compositional. Generalization Logical semantics: generalize using composition and abstract recursive structures. Machine Learning (classification): learns generalizations through real-world examples (e.g. target input-output) Bridge: get our learning to target compositional structures. 15
34 A simple model: Liang and Potts Model: a simple discriminative learning framework. compositional model: (semantic) context-free grammar. learning model: linear classification and first-order optimization. 16
35 Compositional Model: Linguistic Objects: < u, s, d > u: utterance s: semantic representation (symbolized as ˆuˆ) d: denotation (symbolized as s ) 17
36 Compositional Model: Linguistic Objects: < u, s, d > u: utterance s: semantic representation (symbolized as ˆuˆ) d: denotation (symbolized as s ) Example: < seven minus five, (- 7 5), 2 > 17
37 Compositional Model: Linguistic Objects: < u, s, d > u: s: d: utterance semantic representation (symbolized as ˆuˆ) denotation (symbolized as s ) Example: < seven minus five, (- 7 5), 2 > < minus times, (* (- 2 2) 2), 0 > 17
38 Compositional Model: Linguistic Objects: < u, s, d > u: s: d: utterance semantic representation (symbolized as ˆuˆ) denotation (symbolized as s ) Example: < seven minus five, (- 7 5), 2 > < minus times, (* (- 2 2) 2), 0 > semantic parsing: u s 17
39 Compositional Model: Linguistic Objects: < u, s, d > u: s: d: utterance semantic representation (symbolized as ˆuˆ) denotation (symbolized as s ) Example: < seven minus five, (- 7 5), 2 > < minus times, (* (- 2 2) 2), 0 > semantic parsing: u s interpretation: s d 17
40 Computational Modeling: The full picture Standard processing pipeline input List samples that contain every major element Semantic Parsing sem (FOR EVERY X / MAJORELT : T; (FOR EVERY Y / SAMPLE : (CONTAINS Y X); (PRINTOUT Y))) Knowledge Representation Interpretation world sem ={S10019,S10059,...} Lunar QA system (Woods (1973)) 18
41 Compositional Model: Context-free grammar provides the background grammar and interpretation rules 19
42 Compositional Model: Context-free grammar provides the background grammar and interpretation rules example: u = times plus three N: (plus (mult 2 2) 3) N : (mult 2 2) R : plus N : 3 R : mult plus three times 20
43 Compositional Model: Context-free grammar provides the background grammar and interpretation rules example: u = times plus three N: (plus (mult 2 2) 3) N : (mult 2 2) R : plus N : 3 R : mult plus three times >>> plus = lambda x,y : x + y >>> mult = lambda x,y : x * y 20
44 Compositional Model: Context-free grammar provides the background grammar and interpretation rules example: u = times plus three N: (plus (mult 2 2) 3) N : (mult 2 2) R : plus N : 3 R : mult plus three times >>> plus = lambda x,y : x + y >>> mult = lambda x,y : x * y >>> plus(2,2) # 4 20
45 Compositional Model: Context-free grammar provides the background grammar and interpretation rules example: u = times plus three N: (plus (mult 2 2) 3) N : (mult 2 2) R : plus N : 3 R : mult plus three times >>> plus = lambda x,y : x + y >>> mult = lambda x,y : x * y >>> plus(plus(2,3),2) # 7 21
46 Compositional Model: Context-free grammar provides the background grammar and interpretation rules example: u = times plus three N: (plus (mult 2 2) 3) N : (mult 2 2) R : plus N : 3 R : mult plus three times >>> plus = lambda x,y : x + y >>> mult = lambda x,y : x * y >>> plus(mult(2,2),3) # 7 22
47 Compositional Model: Components Components: Grammar rules for building syntactic structure. 23
48 Compositional Model: Components Components: Grammar rules for building syntactic structure. Interpretation rules to composing meaning. 23
49 Compositional Model: Components Components: Grammar rules for building syntactic structure. Interpretation rules to composing meaning. Decoding algorithm for generating structures (later lecture) 23
50 Compositional Model: Components Components: Grammar rules for building syntactic structure. Interpretation rules to composing meaning. Decoding algorithm for generating structures (later lecture) Rule extraction (later lecture) 23
51 Compositional Model: Components Components: Grammar rules for building syntactic structure. Interpretation rules to composing meaning. Decoding algorithm for generating structures (later lecture) Rule extraction (later lecture) Issues: 23
52 Compositional Model: Components Components: Grammar rules for building syntactic structure. Interpretation rules to composing meaning. Decoding algorithm for generating structures (later lecture) Rule extraction (later lecture) Issues: example: u = times plus three N: (plus (mult 2 2) 3) N: (plus (plus 2 2) 3) N : (mult 2 2) R : plus N : 3 N : (plus 2 2) R : plus N : 3 R : mult plus three R : plus plus three times times 23
53 Compositional Model: Components Components: Grammar rules for building syntactic structure. Interpretation rules to composing meaning. Decoding algorithm for generating structures (later lecture) Issues: example: u = times plus three N: (plus (mult 2 2) 3) N: (mult (plus 2 2) 3) N : (mult 2 2) R : plus N : 3 N : (plus 2 2) R : mult N : 3 R : mult plus three R : mult plus three times times 24
54 Compositional Model: Components Components: Grammar rules for building syntactic structure. Interpretation rules to composing meaning. Decoding algorithm for generating structures (later lecture) Issues: example: u = times plus three N: (plus (mult 2 2) 3) N: (mult 2 (plus 2 3)) N : (mult 2 2) R : plus N : 3 R : mult N : (plus 2 3) R : mult plus three times R: plus N : 3 times plus three 25
55 Learning Model Goal: Helps us learn the correct derivations and handle uncertainty (word mappings, composition). Classifier: a system that inputs a vector of discrete and/or continuous feature values and outputs a single discrete value, the class. Domingos (2012). 26
56 Learning Model Goal: Helps us learn the correct derivations and handle uncertainty (word mappings, composition). Classifier: a system that inputs a vector of discrete and/or continuous feature values and outputs a single discrete value, the class. Domingos (2012). 26
57 Learning Model Goal: Helps us learn the correct derivations and handle uncertainty (word mappings, composition). Classifier: a system that inputs a vector of discrete and/or continuous feature values and outputs a single discrete value, the class. Domingos (2012). Components 26
58 Learning Model Goal: Helps us learn the correct derivations and handle uncertainty (word mappings, composition). Classifier: a system that inputs a vector of discrete and/or continuous feature values and outputs a single discrete value, the class. Domingos (2012). Components training data D = {(xi, y i ) i...n} 26
59 Learning Model Goal: Helps us learn the correct derivations and handle uncertainty (word mappings, composition). Classifier: a system that inputs a vector of discrete and/or continuous feature values and outputs a single discrete value, the class. Domingos (2012). Components training data D = {(xi, y i ) i...n} feature representation of data 26
60 Learning Model Goal: Helps us learn the correct derivations and handle uncertainty (word mappings, composition). Classifier: a system that inputs a vector of discrete and/or continuous feature values and outputs a single discrete value, the class. Domingos (2012). Components training data D = {(xi, y i ) i...n} feature representation of data scoring and objective function 26
61 Learning Model Goal: Helps us learn the correct derivations and handle uncertainty (word mappings, composition). Classifier: a system that inputs a vector of discrete and/or continuous feature values and outputs a single discrete value, the class. Domingos (2012). Components training data D = {(xi, y i ) i...n} feature representation of data scoring and objective function optimization procedure 26
62 Training data Goal: Find the correct derivations and output using our compositional model 27
63 Training data Goal: Find the correct derivations and output using our compositional model Logical forms (more information) (u = minus times, s = (* (- 2 2) 2)) 27
64 Training data Goal: Find the correct derivations and output using our compositional model Logical forms (more information) (u = minus times, s = (* (- 2 2) 2)) Denotations (less information) (u = minus times, r = 0) 27
65 Training data Goal: Find the correct derivations and output using our compositional model Logical forms (more information) (u = minus times, s = (* (- 2 2) 2)) Denotations (less information) (u = minus times, r = 0) Weakly Supervised: the learner. In both cases, details are still hidden from 27
66 Learning from Semantic Representations example: ( times plus three,(plus (mult 2 2) 3)) N: (plus (mult 2 2) 3) N: (plus (plus 2 2) 3) N : (mult 2 2) R : plus N : 3 N : (plus 2 2) R : plus N : 3 R : mul plus three R : plus plus three times times 28
67 Learning from Semantic Representations example: ( times plus three,(plus (mult 2 2) 3)) N: (plus (mult 2 2) 3) N: (plus (plus 2 2) 3) N : (mult 2 2) R : plus N : 3 N : (plus 2 2) R : plus N : 3 R : mul plus three R : plus plus three times times Trade off: More information (good) but more annotation (bad) 28
68 Learning from Denotations example: ( times plus three,7) N: (plus (mult 2 2) 3) N: (plus (plus 2 2) 3) N : (mult 2 2) R : plus N : 3 N : (plus 2 2) R : plus N : 3 R : mul plus three R : plus plus three times times 29
69 Learning from Denotations example: ( times plus three,7) N: (plus (mult 2 2) 3) N: (plus (plus 2 2) 3) N : (mult 2 2) R : plus N : 3 N : (plus 2 2) R : plus N : 3 R : mul plus three R : plus plus three times times Trade off: Less annotation (good) but less information (maybe bad) 29
70 Weak Supervision Goal: Find the correct derivations and output using our compositional model Logical forms (more information) (u = minus times, s = (* (- 2 2) 2)) Denotations (less information) (u = minus times, r = 0) Current learning methods for NLP require annotating large corpora with supervisory information...[e.g. pos tags, syntactic parse trees, semantic role labels]... Building such corpora is an expensive, arduous task. As one moves towards deeper semantic analysis the annotation task becomes increasingly more difficult and complex. Mooney (2008) 30
71 Feature Representations: General Remark At the end of the day, some machine learning projects succeed and fail. What makes the difference? Easily the most important factor is the features used. Domingos (2012) 31
72 Feature selection and overfitting What if the knowledge and data we have are not sufficient to completely determine the correct classifier? Then we run the risk of just hallucinating a classifier (or parts of it) that is not grounded in reality.. This problem is called overfitting. Domingos (2012) Bias: Tendency to consistently learn the wrong thing. Variance: Tendency to learn random things irrespective of the real signal. 32
73 Good vs. Bad Feature Selection 33
74 Feature Extraction Example input: x = times plus three. y 1 = N: (plus (mult 2 2) 3) y 2 = N: (plus (plus 2 2) 3) N : (mult 2 2) R : plus N : 3 N : (plus 2 2) R : plus N : 3 R : mult plus three R : plus plus three times times φ(x,y 1 ) = R : mult [ times ] 1 R : plus [ plus ] 1 top [ R : plus ] 1... φ(x,y 2 ) = R : plus [ times ] 1 R : plus [ plus ] 1 top [ R : plus ]
75 Scoring Function (Linear) Score Function Score w (x,y) = w φ(x, y) = d j=1 w jφ(x, y) 35
76 Scoring Function (Linear) Score Function Score w (x,y) = w φ(x, y) = d j=1 w jφ(x, y) weight vector w = [w 1 = 0.1 w 2 = 0.2 w 3 = ] 35
77 Scoring Function (Linear) Score Function Score w (x,y) = w φ(x, y) = d j=1 w jφ(x, y) weight vector w = [w 1 = 0.1 w 2 = 0.2 w 3 = ] φ(x,y 2 ) = w 1 R : plus [ times ] 1 w 2 R : plus [ plus ] 1 w 3 top [ R : plus ] 1... score w (x, y 2 ) = w φ(x, y 2 ) = ( ) + ( ) + ( ) 35
78 Scoring Function (Linear) Score Function Score w (x,y) = w φ(x, y) = d j=1 w jφ(x, y) weight vector w = [w 1 = 0.1 w 2 = 0.2 w 3 = ] prediction: arg-max y Y Score w (x, y) 36
79 Objectives: What do we want to learn? (informal) General Idea: want to learn a model (or weight vector) that can distinguish correct and incorrect derivations. y 1 = N: (plus (mult 2 2) 3) y 2 = N: (plus (plus 2 2) 3) N : (mult 2 2) R : plus N : 3 N : (plus 2 2) R : plus N : 3 R : mult plus three R : plus plus three times times φ(x,y 1 ) = R : mult [ times ] 1 R : plus [ plus ] 1 top [ R : plus ] 1... φ(x,y 2 ) = R : plus [ times ] 1 R : plus [ plus ] 1 top [ R : plus ]
80 Objectives: What do we want to learn? (informal) General Idea: want to learn a model (or weight vector) that can distinguish correct and incorrect derivations. y 1 = N: (plus (mult 2 2) 3) N: (mult 2 (plus 2 3)) N : (mult 2 2) R : plus N : 3 R : mult N : (plus 2 3) R : mult plus three times R: plus N : 3 times plus three φ(x,y 1 ) = R : mult [ times ] 1 R : plus [ plus ] 1 plus [ R : mult ] 1... φ(x,y 2 ) = R : plus [ times ] 1 R : plus [ plus ] 1 mult [ R : plus ]
81 Objectives: What do we want to learn? (formal) hinge loss: (learning from logical forms) min w R d n max y Y [Score w (x, y )+c(y, y )] Score w (x, y) (x,y) D ( minus times, s = (* (- 2 2) 2)) 39
82 Objectives: What do we want to learn? (formal) hinge loss: (learning from logical forms) min w R d n (x,y) D max y Y [Score w (x, y )+c(y, y )] Score w (x, y) ( minus times, s = (* (- 2 2) 2)) In English: select parameters that minimize the cumulative loss over the training data. 39
83 Objectives: What do we want to learn? (formal) hinge loss: (learning from logical forms) min w R d n (x,y) D max y Y [Score w (x, y )+c(y, y )] Score w (x, y) ( minus times, s = (* (- 2 2) 2)) In English: select parameters that minimize the cumulative loss over the training data. Missing: A decoding algorithm for generating Y (not trivial, Y might be very large). 39
84 Optimization: How do I achieve this objective? Stochastic gradient descent: An online learning and optimization algorithm (more about this in future lectures). 40
85 Optimization: Illustration 41
86 Learning Model Components training data: D = {(xi, y i ) i...n} 42
87 Learning Model Components training data: D = {(xi, y i ) i...n} feature representation of data 42
88 Learning Model Components training data: D = {(xi, y i ) i...n} feature representation of data scoring and objective function 42
89 Learning Model Components training data: D = {(xi, y i ) i...n} feature representation of data scoring and objective function optimization procedure 42
90 Learning Model Components training data: D = {(xi, y i ) i...n} feature representation of data scoring and objective function optimization procedure Important Ideas What kind of data do we learn from? (differs quite a bit) What kind of features do we need? 42
91 Experimentation and Evaluation Training Set: Test Set: A portion of the data to train model on. An unseen portion of the data to evaluate on. Dev Set : (optional) An unseen portion of the data for analysis, tuning hyper parameters,.. 43
92 Experimentation and Evaluation Training Set: Test Set: A portion of the data to train model on. An unseen portion of the data to evaluate on. Dev Set : (optional) An unseen portion of the data for analysis, tuning hyper parameters,.. Evaluation1: Given unseen examples, how often does my model produce the correct output semantic representation? Evaluation2: Given unseen examples, how often does my model produce the correct output answer? 43
93 Conclusions and Take Aways Presented a simple model that mixes machine learning and compositional semantics. Conceptually describes most of the work in this class. Technically describes many of the models we will use. Fundamental Problem: Which semantics representations do we use, and what do we learn from? 44
94 Conclusions and Take Aways Presented a simple model that mixes machine learning and compositional semantics. Conceptually describes most of the work in this class. Technically describes many of the models we will use. Fundamental Problem: Which semantics representations do we use, and what do we learn from? Question: Does this particular actually work? 44
95 Conclusions and Take Aways Presented a simple model that mixes machine learning and compositional semantics. Conceptually describes most of the work in this class. Technically describes many of the models we will use. Fundamental Problem: Which semantics representations do we use, and what do we learn from? Question: Does this particular actually work? Yes! Liang et al. (2011) (lecture 5), Berant et al. (2013); Berant and Liang (2014) (presentation papers) 44
96 Roadmap Lecture 2: Lecture 3: Lecture 4: Lecture 5: rule extraction, decoding (parsing perspective) rule extraction, decoding (MT perspective) structured classification and prediction. grounded learning (might skip). 45
97 References I Berant, J., Chou, A., Frostig, R., and Liang, P. (2013). Semantic parsing on Freebase from question-answer pairs. In in Proceedings of EMNLP-2013, pages Berant, J. and Liang, P. (2014). Semantic parsing via paraphrasing. In ACL (1), pages Domingos, P. (2012). A few useful things to know about machine learning. Communications of the ACM, 55(10): Liang, P., Jordan, M. I., and Klein, D. (2011). Learning dependency-based compositional semantics. In Proceedings of ACL-11, pages Mooney, R. (2008). Learning to connect language and perception. In Proceedings of AAAI Turney, P. D., Pantel, P., et al. (2010). From frequency to meaning: Vector space models of semantics. Journal of artificial intelligence research, 37(1): Woods, W. A. (1973). Progress in natural language understanding: an application to lunar geology. In Proceedings of the June 4-8, 1973, National Computer Conference and Exposition, pages
Python Machine Learning
Python Machine Learning Unlock deeper insights into machine learning with this vital guide to cuttingedge predictive analytics Sebastian Raschka [ PUBLISHING 1 open source I community experience distilled
More informationLecture 1: Machine Learning Basics
1/69 Lecture 1: Machine Learning Basics Ali Harakeh University of Waterloo WAVE Lab ali.harakeh@uwaterloo.ca May 1, 2017 2/69 Overview 1 Learning Algorithms 2 Capacity, Overfitting, and Underfitting 3
More information(Sub)Gradient Descent
(Sub)Gradient Descent CMSC 422 MARINE CARPUAT marine@cs.umd.edu Figures credit: Piyush Rai Logistics Midterm is on Thursday 3/24 during class time closed book/internet/etc, one page of notes. will include
More informationSemi-supervised methods of text processing, and an application to medical concept extraction. Yacine Jernite Text-as-Data series September 17.
Semi-supervised methods of text processing, and an application to medical concept extraction Yacine Jernite Text-as-Data series September 17. 2015 What do we want from text? 1. Extract information 2. Link
More informationCSL465/603 - Machine Learning
CSL465/603 - Machine Learning Fall 2016 Narayanan C Krishnan ckn@iitrpr.ac.in Introduction CSL465/603 - Machine Learning 1 Administrative Trivia Course Structure 3-0-2 Lecture Timings Monday 9.55-10.45am
More informationCS Machine Learning
CS 478 - Machine Learning Projects Data Representation Basic testing and evaluation schemes CS 478 Data and Testing 1 Programming Issues l Program in any platform you want l Realize that you will be doing
More informationModule 12. Machine Learning. Version 2 CSE IIT, Kharagpur
Module 12 Machine Learning 12.1 Instructional Objective The students should understand the concept of learning systems Students should learn about different aspects of a learning system Students should
More informationMachine Learning and Data Mining. Ensembles of Learners. Prof. Alexander Ihler
Machine Learning and Data Mining Ensembles of Learners Prof. Alexander Ihler Ensemble methods Why learn one classifier when you can learn many? Ensemble: combine many predictors (Weighted) combina
More informationUsing dialogue context to improve parsing performance in dialogue systems
Using dialogue context to improve parsing performance in dialogue systems Ivan Meza-Ruiz and Oliver Lemon School of Informatics, Edinburgh University 2 Buccleuch Place, Edinburgh I.V.Meza-Ruiz@sms.ed.ac.uk,
More informationSpeech Recognition at ICSI: Broadcast News and beyond
Speech Recognition at ICSI: Broadcast News and beyond Dan Ellis International Computer Science Institute, Berkeley CA Outline 1 2 3 The DARPA Broadcast News task Aspects of ICSI
More informationA Case Study: News Classification Based on Term Frequency
A Case Study: News Classification Based on Term Frequency Petr Kroha Faculty of Computer Science University of Technology 09107 Chemnitz Germany kroha@informatik.tu-chemnitz.de Ricardo Baeza-Yates Center
More informationProbabilistic Latent Semantic Analysis
Probabilistic Latent Semantic Analysis Thomas Hofmann Presentation by Ioannis Pavlopoulos & Andreas Damianou for the course of Data Mining & Exploration 1 Outline Latent Semantic Analysis o Need o Overview
More informationDeep search. Enhancing a search bar using machine learning. Ilgün Ilgün & Cedric Reichenbach
#BaselOne7 Deep search Enhancing a search bar using machine learning Ilgün Ilgün & Cedric Reichenbach We are not researchers Outline I. Periscope: A search tool II. Goals III. Deep learning IV. Applying
More informationLecture 1: Basic Concepts of Machine Learning
Lecture 1: Basic Concepts of Machine Learning Cognitive Systems - Machine Learning Ute Schmid (lecture) Johannes Rabold (practice) Based on slides prepared March 2005 by Maximilian Röglinger, updated 2010
More informationLinking Task: Identifying authors and book titles in verbose queries
Linking Task: Identifying authors and book titles in verbose queries Anaïs Ollagnier, Sébastien Fournier, and Patrice Bellot Aix-Marseille University, CNRS, ENSAM, University of Toulon, LSIS UMR 7296,
More informationApplications of memory-based natural language processing
Applications of memory-based natural language processing Antal van den Bosch and Roser Morante ILK Research Group Tilburg University Prague, June 24, 2007 Current ILK members Principal investigator: Antal
More informationAssignment 1: Predicting Amazon Review Ratings
Assignment 1: Predicting Amazon Review Ratings 1 Dataset Analysis Richard Park r2park@acsmail.ucsd.edu February 23, 2015 The dataset selected for this assignment comes from the set of Amazon reviews for
More informationSystem Implementation for SemEval-2017 Task 4 Subtask A Based on Interpolated Deep Neural Networks
System Implementation for SemEval-2017 Task 4 Subtask A Based on Interpolated Deep Neural Networks 1 Tzu-Hsuan Yang, 2 Tzu-Hsuan Tseng, and 3 Chia-Ping Chen Department of Computer Science and Engineering
More informationCalibration of Confidence Measures in Speech Recognition
Submitted to IEEE Trans on Audio, Speech, and Language, July 2010 1 Calibration of Confidence Measures in Speech Recognition Dong Yu, Senior Member, IEEE, Jinyu Li, Member, IEEE, Li Deng, Fellow, IEEE
More informationArtificial Neural Networks written examination
1 (8) Institutionen för informationsteknologi Olle Gällmo Universitetsadjunkt Adress: Lägerhyddsvägen 2 Box 337 751 05 Uppsala Artificial Neural Networks written examination Monday, May 15, 2006 9 00-14
More informationThe stages of event extraction
The stages of event extraction David Ahn Intelligent Systems Lab Amsterdam University of Amsterdam ahn@science.uva.nl Abstract Event detection and recognition is a complex task consisting of multiple sub-tasks
More informationAQUA: An Ontology-Driven Question Answering System
AQUA: An Ontology-Driven Question Answering System Maria Vargas-Vera, Enrico Motta and John Domingue Knowledge Media Institute (KMI) The Open University, Walton Hall, Milton Keynes, MK7 6AA, United Kingdom.
More informationUnsupervised Learning of Word Semantic Embedding using the Deep Structured Semantic Model
Unsupervised Learning of Word Semantic Embedding using the Deep Structured Semantic Model Xinying Song, Xiaodong He, Jianfeng Gao, Li Deng Microsoft Research, One Microsoft Way, Redmond, WA 98052, U.S.A.
More informationarxiv: v1 [cs.cl] 2 Apr 2017
Word-Alignment-Based Segment-Level Machine Translation Evaluation using Word Embeddings Junki Matsuo and Mamoru Komachi Graduate School of System Design, Tokyo Metropolitan University, Japan matsuo-junki@ed.tmu.ac.jp,
More informationIntroduction to Simulation
Introduction to Simulation Spring 2010 Dr. Louis Luangkesorn University of Pittsburgh January 19, 2010 Dr. Louis Luangkesorn ( University of Pittsburgh ) Introduction to Simulation January 19, 2010 1 /
More informationSecond Exam: Natural Language Parsing with Neural Networks
Second Exam: Natural Language Parsing with Neural Networks James Cross May 21, 2015 Abstract With the advent of deep learning, there has been a recent resurgence of interest in the use of artificial neural
More informationOPTIMIZATINON OF TRAINING SETS FOR HEBBIAN-LEARNING- BASED CLASSIFIERS
OPTIMIZATINON OF TRAINING SETS FOR HEBBIAN-LEARNING- BASED CLASSIFIERS Václav Kocian, Eva Volná, Michal Janošek, Martin Kotyrba University of Ostrava Department of Informatics and Computers Dvořákova 7,
More informationLearning Structural Correspondences Across Different Linguistic Domains with Synchronous Neural Language Models
Learning Structural Correspondences Across Different Linguistic Domains with Synchronous Neural Language Models Stephan Gouws and GJ van Rooyen MIH Medialab, Stellenbosch University SOUTH AFRICA {stephan,gvrooyen}@ml.sun.ac.za
More informationSpecification and Evaluation of Machine Translation Toy Systems - Criteria for laboratory assignments
Specification and Evaluation of Machine Translation Toy Systems - Criteria for laboratory assignments Cristina Vertan, Walther v. Hahn University of Hamburg, Natural Language Systems Division Hamburg,
More informationExperiments with SMS Translation and Stochastic Gradient Descent in Spanish Text Author Profiling
Experiments with SMS Translation and Stochastic Gradient Descent in Spanish Text Author Profiling Notebook for PAN at CLEF 2013 Andrés Alfonso Caurcel Díaz 1 and José María Gómez Hidalgo 2 1 Universidad
More informationEvolutive Neural Net Fuzzy Filtering: Basic Description
Journal of Intelligent Learning Systems and Applications, 2010, 2: 12-18 doi:10.4236/jilsa.2010.21002 Published Online February 2010 (http://www.scirp.org/journal/jilsa) Evolutive Neural Net Fuzzy Filtering:
More informationActive Learning. Yingyu Liang Computer Sciences 760 Fall
Active Learning Yingyu Liang Computer Sciences 760 Fall 2017 http://pages.cs.wisc.edu/~yliang/cs760/ Some of the slides in these lectures have been adapted/borrowed from materials developed by Mark Craven,
More informationKnowledge Transfer in Deep Convolutional Neural Nets
Knowledge Transfer in Deep Convolutional Neural Nets Steven Gutstein, Olac Fuentes and Eric Freudenthal Computer Science Department University of Texas at El Paso El Paso, Texas, 79968, U.S.A. Abstract
More informationExtracting Opinion Expressions and Their Polarities Exploration of Pipelines and Joint Models
Extracting Opinion Expressions and Their Polarities Exploration of Pipelines and Joint Models Richard Johansson and Alessandro Moschitti DISI, University of Trento Via Sommarive 14, 38123 Trento (TN),
More informationProof Theory for Syntacticians
Department of Linguistics Ohio State University Syntax 2 (Linguistics 602.02) January 5, 2012 Logics for Linguistics Many different kinds of logic are directly applicable to formalizing theories in syntax
More informationSpoken Language Parsing Using Phrase-Level Grammars and Trainable Classifiers
Spoken Language Parsing Using Phrase-Level Grammars and Trainable Classifiers Chad Langley, Alon Lavie, Lori Levin, Dorcas Wallace, Donna Gates, and Kay Peterson Language Technologies Institute Carnegie
More informationIntroduction to Ensemble Learning Featuring Successes in the Netflix Prize Competition
Introduction to Ensemble Learning Featuring Successes in the Netflix Prize Competition Todd Holloway Two Lecture Series for B551 November 20 & 27, 2007 Indiana University Outline Introduction Bias and
More informationOnline Updating of Word Representations for Part-of-Speech Tagging
Online Updating of Word Representations for Part-of-Speech Tagging Wenpeng Yin LMU Munich wenpeng@cis.lmu.de Tobias Schnabel Cornell University tbs49@cornell.edu Hinrich Schütze LMU Munich inquiries@cislmu.org
More informationMachine Learning from Garden Path Sentences: The Application of Computational Linguistics
Machine Learning from Garden Path Sentences: The Application of Computational Linguistics http://dx.doi.org/10.3991/ijet.v9i6.4109 J.L. Du 1, P.F. Yu 1 and M.L. Li 2 1 Guangdong University of Foreign Studies,
More informationA Comparison of Two Text Representations for Sentiment Analysis
010 International Conference on Computer Application and System Modeling (ICCASM 010) A Comparison of Two Text Representations for Sentiment Analysis Jianxiong Wang School of Computer Science & Educational
More informationModeling function word errors in DNN-HMM based LVCSR systems
Modeling function word errors in DNN-HMM based LVCSR systems Melvin Jose Johnson Premkumar, Ankur Bapna and Sree Avinash Parchuri Department of Computer Science Department of Electrical Engineering Stanford
More informationLanguage Acquisition Fall 2010/Winter Lexical Categories. Afra Alishahi, Heiner Drenhaus
Language Acquisition Fall 2010/Winter 2011 Lexical Categories Afra Alishahi, Heiner Drenhaus Computational Linguistics and Phonetics Saarland University Children s Sensitivity to Lexical Categories Look,
More informationChapter 2 Rule Learning in a Nutshell
Chapter 2 Rule Learning in a Nutshell This chapter gives a brief overview of inductive rule learning and may therefore serve as a guide through the rest of the book. Later chapters will expand upon the
More informationChinese Language Parsing with Maximum-Entropy-Inspired Parser
Chinese Language Parsing with Maximum-Entropy-Inspired Parser Heng Lian Brown University Abstract The Chinese language has many special characteristics that make parsing difficult. The performance of state-of-the-art
More informationPREDICTING SPEECH RECOGNITION CONFIDENCE USING DEEP LEARNING WITH WORD IDENTITY AND SCORE FEATURES
PREDICTING SPEECH RECOGNITION CONFIDENCE USING DEEP LEARNING WITH WORD IDENTITY AND SCORE FEATURES Po-Sen Huang, Kshitiz Kumar, Chaojun Liu, Yifan Gong, Li Deng Department of Electrical and Computer Engineering,
More informationModeling function word errors in DNN-HMM based LVCSR systems
Modeling function word errors in DNN-HMM based LVCSR systems Melvin Jose Johnson Premkumar, Ankur Bapna and Sree Avinash Parchuri Department of Computer Science Department of Electrical Engineering Stanford
More informationBeyond the Pipeline: Discrete Optimization in NLP
Beyond the Pipeline: Discrete Optimization in NLP Tomasz Marciniak and Michael Strube EML Research ggmbh Schloss-Wolfsbrunnenweg 33 69118 Heidelberg, Germany http://www.eml-research.de/nlp Abstract We
More informationNatural Language Processing. George Konidaris
Natural Language Processing George Konidaris gdk@cs.brown.edu Fall 2017 Natural Language Processing Understanding spoken/written sentences in a natural language. Major area of research in AI. Why? Humans
More informationParsing of part-of-speech tagged Assamese Texts
IJCSI International Journal of Computer Science Issues, Vol. 6, No. 1, 2009 ISSN (Online): 1694-0784 ISSN (Print): 1694-0814 28 Parsing of part-of-speech tagged Assamese Texts Mirzanur Rahman 1, Sufal
More informationSouth Carolina English Language Arts
South Carolina English Language Arts A S O F J U N E 2 0, 2 0 1 0, T H I S S TAT E H A D A D O P T E D T H E CO M M O N CO R E S TAT E S TA N DA R D S. DOCUMENTS REVIEWED South Carolina Academic Content
More informationEnsemble Technique Utilization for Indonesian Dependency Parser
Ensemble Technique Utilization for Indonesian Dependency Parser Arief Rahman Institut Teknologi Bandung Indonesia 23516008@std.stei.itb.ac.id Ayu Purwarianti Institut Teknologi Bandung Indonesia ayu@stei.itb.ac.id
More informationSchool of Innovative Technologies and Engineering
School of Innovative Technologies and Engineering Department of Applied Mathematical Sciences Proficiency Course in MATLAB COURSE DOCUMENT VERSION 1.0 PCMv1.0 July 2012 University of Technology, Mauritius
More informationUsing Web Searches on Important Words to Create Background Sets for LSI Classification
Using Web Searches on Important Words to Create Background Sets for LSI Classification Sarah Zelikovitz and Marina Kogan College of Staten Island of CUNY 2800 Victory Blvd Staten Island, NY 11314 Abstract
More informationCompositional Semantics
Compositional Semantics CMSC 723 / LING 723 / INST 725 MARINE CARPUAT marine@cs.umd.edu Words, bag of words Sequences Trees Meaning Representing Meaning An important goal of NLP/AI: convert natural language
More information11/29/2010. Statistical Parsing. Statistical Parsing. Simple PCFG for ATIS English. Syntactic Disambiguation
tatistical Parsing (Following slides are modified from Prof. Raymond Mooney s slides.) tatistical Parsing tatistical parsing uses a probabilistic model of syntax in order to assign probabilities to each
More informationRule Learning With Negation: Issues Regarding Effectiveness
Rule Learning With Negation: Issues Regarding Effectiveness S. Chua, F. Coenen, G. Malcolm University of Liverpool Department of Computer Science, Ashton Building, Ashton Street, L69 3BX Liverpool, United
More informationBYLINE [Heng Ji, Computer Science Department, New York University,
INFORMATION EXTRACTION BYLINE [Heng Ji, Computer Science Department, New York University, hengji@cs.nyu.edu] SYNONYMS NONE DEFINITION Information Extraction (IE) is a task of extracting pre-specified types
More informationSTA 225: Introductory Statistics (CT)
Marshall University College of Science Mathematics Department STA 225: Introductory Statistics (CT) Course catalog description A critical thinking course in applied statistical reasoning covering basic
More informationSoftprop: Softmax Neural Network Backpropagation Learning
Softprop: Softmax Neural Networ Bacpropagation Learning Michael Rimer Computer Science Department Brigham Young University Provo, UT 84602, USA E-mail: mrimer@axon.cs.byu.edu Tony Martinez Computer Science
More informationarxiv: v1 [cs.lg] 15 Jun 2015
Dual Memory Architectures for Fast Deep Learning of Stream Data via an Online-Incremental-Transfer Strategy arxiv:1506.04477v1 [cs.lg] 15 Jun 2015 Sang-Woo Lee Min-Oh Heo School of Computer Science and
More informationWord Segmentation of Off-line Handwritten Documents
Word Segmentation of Off-line Handwritten Documents Chen Huang and Sargur N. Srihari {chuang5, srihari}@cedar.buffalo.edu Center of Excellence for Document Analysis and Recognition (CEDAR), Department
More informationAxiom 2013 Team Description Paper
Axiom 2013 Team Description Paper Mohammad Ghazanfari, S Omid Shirkhorshidi, Farbod Samsamipour, Hossein Rahmatizadeh Zagheli, Mohammad Mahdavi, Payam Mohajeri, S Abbas Alamolhoda Robotics Scientific Association
More informationhave to be modeled) or isolated words. Output of the system is a grapheme-tophoneme conversion system which takes as its input the spelling of words,
A Language-Independent, Data-Oriented Architecture for Grapheme-to-Phoneme Conversion Walter Daelemans and Antal van den Bosch Proceedings ESCA-IEEE speech synthesis conference, New York, September 1994
More informationINPE São José dos Campos
INPE-5479 PRE/1778 MONLINEAR ASPECTS OF DATA INTEGRATION FOR LAND COVER CLASSIFICATION IN A NEDRAL NETWORK ENVIRONNENT Maria Suelena S. Barros Valter Rodrigues INPE São José dos Campos 1993 SECRETARIA
More informationCS 446: Machine Learning
CS 446: Machine Learning Introduction to LBJava: a Learning Based Programming Language Writing classifiers Christos Christodoulopoulos Parisa Kordjamshidi Motivation 2 Motivation You still have not learnt
More informationCS 598 Natural Language Processing
CS 598 Natural Language Processing Natural language is everywhere Natural language is everywhere Natural language is everywhere Natural language is everywhere!"#$%&'&()*+,-./012 34*5665756638/9:;< =>?@ABCDEFGHIJ5KL@
More informationVersion Space. Term 2012/2013 LSI - FIB. Javier Béjar cbea (LSI - FIB) Version Space Term 2012/ / 18
Version Space Javier Béjar cbea LSI - FIB Term 2012/2013 Javier Béjar cbea (LSI - FIB) Version Space Term 2012/2013 1 / 18 Outline 1 Learning logical formulas 2 Version space Introduction Search strategy
More informationPOS tagging of Chinese Buddhist texts using Recurrent Neural Networks
POS tagging of Chinese Buddhist texts using Recurrent Neural Networks Longlu Qin Department of East Asian Languages and Cultures longlu@stanford.edu Abstract Chinese POS tagging, as one of the most important
More informationA study of speaker adaptation for DNN-based speech synthesis
A study of speaker adaptation for DNN-based speech synthesis Zhizheng Wu, Pawel Swietojanski, Christophe Veaux, Steve Renals, Simon King The Centre for Speech Technology Research (CSTR) University of Edinburgh,
More informationThe Internet as a Normative Corpus: Grammar Checking with a Search Engine
The Internet as a Normative Corpus: Grammar Checking with a Search Engine Jonas Sjöbergh KTH Nada SE-100 44 Stockholm, Sweden jsh@nada.kth.se Abstract In this paper some methods using the Internet as a
More informationarxiv: v1 [cs.cl] 20 Jul 2015
How to Generate a Good Word Embedding? Siwei Lai, Kang Liu, Liheng Xu, Jun Zhao National Laboratory of Pattern Recognition (NLPR) Institute of Automation, Chinese Academy of Sciences, China {swlai, kliu,
More informationKLI: Infer KCs from repeated assessment events. Do you know what you know? Ken Koedinger HCI & Psychology CMU Director of LearnLab
KLI: Infer KCs from repeated assessment events Ken Koedinger HCI & Psychology CMU Director of LearnLab Instructional events Explanation, practice, text, rule, example, teacher-student discussion Learning
More informationWHEN THERE IS A mismatch between the acoustic
808 IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 14, NO. 3, MAY 2006 Optimization of Temporal Filters for Constructing Robust Features in Speech Recognition Jeih-Weih Hung, Member,
More informationEnhancing Unlexicalized Parsing Performance using a Wide Coverage Lexicon, Fuzzy Tag-set Mapping, and EM-HMM-based Lexical Probabilities
Enhancing Unlexicalized Parsing Performance using a Wide Coverage Lexicon, Fuzzy Tag-set Mapping, and EM-HMM-based Lexical Probabilities Yoav Goldberg Reut Tsarfaty Meni Adler Michael Elhadad Ben Gurion
More informationAUTOMATIC DETECTION OF PROLONGED FRICATIVE PHONEMES WITH THE HIDDEN MARKOV MODELS APPROACH 1. INTRODUCTION
JOURNAL OF MEDICAL INFORMATICS & TECHNOLOGIES Vol. 11/2007, ISSN 1642-6037 Marek WIŚNIEWSKI *, Wiesława KUNISZYK-JÓŹKOWIAK *, Elżbieta SMOŁKA *, Waldemar SUSZYŃSKI * HMM, recognition, speech, disorders
More informationGenerative models and adversarial training
Day 4 Lecture 1 Generative models and adversarial training Kevin McGuinness kevin.mcguinness@dcu.ie Research Fellow Insight Centre for Data Analytics Dublin City University What is a generative model?
More informationObjectives. Chapter 2: The Representation of Knowledge. Expert Systems: Principles and Programming, Fourth Edition
Chapter 2: The Representation of Knowledge Expert Systems: Principles and Programming, Fourth Edition Objectives Introduce the study of logic Learn the difference between formal logic and informal logic
More informationUsing the Attribute Hierarchy Method to Make Diagnostic Inferences about Examinees Cognitive Skills in Algebra on the SAT
The Journal of Technology, Learning, and Assessment Volume 6, Number 6 February 2008 Using the Attribute Hierarchy Method to Make Diagnostic Inferences about Examinees Cognitive Skills in Algebra on the
More informationAttributed Social Network Embedding
JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, MAY 2017 1 Attributed Social Network Embedding arxiv:1705.04969v1 [cs.si] 14 May 2017 Lizi Liao, Xiangnan He, Hanwang Zhang, and Tat-Seng Chua Abstract Embedding
More informationTarget Language Preposition Selection an Experiment with Transformation-Based Learning and Aligned Bilingual Data
Target Language Preposition Selection an Experiment with Transformation-Based Learning and Aligned Bilingual Data Ebba Gustavii Department of Linguistics and Philology, Uppsala University, Sweden ebbag@stp.ling.uu.se
More informationEvolution of Symbolisation in Chimpanzees and Neural Nets
Evolution of Symbolisation in Chimpanzees and Neural Nets Angelo Cangelosi Centre for Neural and Adaptive Systems University of Plymouth (UK) a.cangelosi@plymouth.ac.uk Introduction Animal communication
More informationExploration. CS : Deep Reinforcement Learning Sergey Levine
Exploration CS 294-112: Deep Reinforcement Learning Sergey Levine Class Notes 1. Homework 4 due on Wednesday 2. Project proposal feedback sent Today s Lecture 1. What is exploration? Why is it a problem?
More informationPrediction of Maximal Projection for Semantic Role Labeling
Prediction of Maximal Projection for Semantic Role Labeling Weiwei Sun, Zhifang Sui Institute of Computational Linguistics Peking University Beijing, 100871, China {ws, szf}@pku.edu.cn Haifeng Wang Toshiba
More informationSome Principles of Automated Natural Language Information Extraction
Some Principles of Automated Natural Language Information Extraction Gregers Koch Department of Computer Science, Copenhagen University DIKU, Universitetsparken 1, DK-2100 Copenhagen, Denmark Abstract
More informationAn investigation of imitation learning algorithms for structured prediction
JMLR: Workshop and Conference Proceedings 24:143 153, 2012 10th European Workshop on Reinforcement Learning An investigation of imitation learning algorithms for structured prediction Andreas Vlachos Computer
More informationDistant Supervised Relation Extraction with Wikipedia and Freebase
Distant Supervised Relation Extraction with Wikipedia and Freebase Marcel Ackermann TU Darmstadt ackermann@tk.informatik.tu-darmstadt.de Abstract In this paper we discuss a new approach to extract relational
More informationSINGLE DOCUMENT AUTOMATIC TEXT SUMMARIZATION USING TERM FREQUENCY-INVERSE DOCUMENT FREQUENCY (TF-IDF)
SINGLE DOCUMENT AUTOMATIC TEXT SUMMARIZATION USING TERM FREQUENCY-INVERSE DOCUMENT FREQUENCY (TF-IDF) Hans Christian 1 ; Mikhael Pramodana Agus 2 ; Derwin Suhartono 3 1,2,3 Computer Science Department,
More informationLearning Optimal Dialogue Strategies: A Case Study of a Spoken Dialogue Agent for
Learning Optimal Dialogue Strategies: A Case Study of a Spoken Dialogue Agent for Email Marilyn A. Walker Jeanne C. Fromer Shrikanth Narayanan walker@research.att.com jeannie@ai.mit.edu shri@research.att.com
More informationB.S/M.A in Mathematics
B.S/M.A in Mathematics The dual Bachelor of Science/Master of Arts in Mathematics program provides an opportunity for individuals to pursue advanced study in mathematics and to develop skills that can
More informationCAAP. Content Analysis Report. Sample College. Institution Code: 9011 Institution Type: 4-Year Subgroup: none Test Date: Spring 2011
CAAP Content Analysis Report Institution Code: 911 Institution Type: 4-Year Normative Group: 4-year Colleges Introduction This report provides information intended to help postsecondary institutions better
More informationA New Perspective on Combining GMM and DNN Frameworks for Speaker Adaptation
A New Perspective on Combining GMM and DNN Frameworks for Speaker Adaptation SLSP-2016 October 11-12 Natalia Tomashenko 1,2,3 natalia.tomashenko@univ-lemans.fr Yuri Khokhlov 3 khokhlov@speechpro.com Yannick
More informationChunk Parsing for Base Noun Phrases using Regular Expressions. Let s first let the variable s0 be the sentence tree of the first sentence.
NLP Lab Session Week 8 October 15, 2014 Noun Phrase Chunking and WordNet in NLTK Getting Started In this lab session, we will work together through a series of small examples using the IDLE window and
More informationWriting Research Articles
Marek J. Druzdzel with minor additions from Peter Brusilovsky University of Pittsburgh School of Information Sciences and Intelligent Systems Program marek@sis.pitt.edu http://www.pitt.edu/~druzdzel Overview
More informationLearning Methods for Fuzzy Systems
Learning Methods for Fuzzy Systems Rudolf Kruse and Andreas Nürnberger Department of Computer Science, University of Magdeburg Universitätsplatz, D-396 Magdeburg, Germany Phone : +49.39.67.876, Fax : +49.39.67.8
More informationSyntax Parsing 1. Grammars and parsing 2. Top-down and bottom-up parsing 3. Chart parsers 4. Bottom-up chart parsing 5. The Earley Algorithm
Syntax Parsing 1. Grammars and parsing 2. Top-down and bottom-up parsing 3. Chart parsers 4. Bottom-up chart parsing 5. The Earley Algorithm syntax: from the Greek syntaxis, meaning setting out together
More informationTechnical Manual Supplement
VERSION 1.0 Technical Manual Supplement The ACT Contents Preface....................................................................... iii Introduction....................................................................
More informationSpeech Emotion Recognition Using Support Vector Machine
Speech Emotion Recognition Using Support Vector Machine Yixiong Pan, Peipei Shen and Liping Shen Department of Computer Technology Shanghai JiaoTong University, Shanghai, China panyixiong@sjtu.edu.cn,
More informationLearning Methods in Multilingual Speech Recognition
Learning Methods in Multilingual Speech Recognition Hui Lin Department of Electrical Engineering University of Washington Seattle, WA 98125 linhui@u.washington.edu Li Deng, Jasha Droppo, Dong Yu, and Alex
More informationIndian Institute of Technology, Kanpur
Indian Institute of Technology, Kanpur Course Project - CS671A POS Tagging of Code Mixed Text Ayushman Sisodiya (12188) {ayushmn@iitk.ac.in} Donthu Vamsi Krishna (15111016) {vamsi@iitk.ac.in} Sandeep Kumar
More information