class19-classify

class19-classify - Introduc)on to Informa)on Retrieval...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Introduc)on to Informa)on Retrieval Recap: Naïve Bayes classifiers   Classify based on prior weight of class and condi<onal parameter for what each word says:   Training is done by coun<ng and dividing:   Don’t forget to smooth 1 Introduc)on to Informa)on Retrieval The rest of text classifica<on   Today:   Vector space methods for Text Classifica<on         Vector space classifica<on using centroids (Rocchio) K Nearest Neighbors Decision boundaries, linear and nonlinear classifiers Dealing with more than 2 classes 2 1 Introduc)on to Informa)on Retrieval Sec.14.1 Recall: Vector Space Representa<on   Each document is a vector, one component for each term (= word).   Normally normalize vectors to unit length.   High ­dimensional vector space:   Terms are axes   10,000+ dimensions, or even 100,000+   Docs are vectors in this space   How can we do classifica<on in this space? 3 Introduc)on to Informa)on Retrieval Sec.14.1 Classifica<on Using Vector Spaces   As before, the training set is a set of documents, each labeled with its class (e.g., topic)   In vector space classifica<on, this set corresponds to a labeled set of points (or, equivalently, vectors) in the vector space   Premise 1: Documents in the same class form a con<guous region of space   Premise 2: Documents from different classes don’t overlap (much)   We define surfaces to delineate classes in the space 4 2 Introduc)on to Informa)on Retrieval Sec.14.1 Documents in a Vector Space Government Science Arts 5 Introduc)on to Informa)on Retrieval Sec.14.1 Test Document of what class? Government Science Arts 6 3 Introduc)on to Informa)on Retrieval Sec.14.1 Test Document = Government Is this similarity hypothesis true in general? Government Science Arts Our main topic today is how to find good separators 7 Introduc)on to Informa)on Retrieval Sec.14.1 Aside: 2D/3D graphs can be misleading 8 4 Introduc)on to Informa)on Retrieval Sec.14.2 Using Rocchio for text classifica<on   Relevance feedback methods can be adapted for text categoriza<on   As noted before, relevance feedback can be viewed as 2 ­class classifica<on   Relevant vs. nonrelevant documents   Use standard d ­idf weighted vectors to represent text documents   For training documents in each category, compute a prototype vector by summing the vectors of the training documents in the category.   Prototype = centroid of members of class   Assign test documents to the category with the closest prototype vector based on cosine similarity. 9 Introduc)on to Informa)on Retrieval Sec.14.2 Illustra<on of Rocchio Text Categoriza<on 10 5 Introduc)on to Informa)on Retrieval Sec.14.2 Defini<on of centroid   Where Dc is the set of all documents that belong to class c and v(d) is the vector space representa<on of d.   Note that centroid will in general not be a unit vector even when the inputs are unit vectors. 11 Introduc)on to Informa)on Retrieval Sec.14.2 Rocchio Proper<es   Forms a simple generaliza<on of the examples in each class (a prototype).   Prototype vector does not need to be averaged or otherwise normalized for length since cosine similarity is insensi<ve to vector length.   Classifica<on is based on similarity to class prototypes.   Does not guarantee classifica<ons are consistent with the given training data. Why not? 12 6 Introduc)on to Informa)on Retrieval Sec.14.2 Rocchio Anomaly   Prototype models have problems with polymorphic (disjunc<ve) categories. 13 Introduc)on to Informa)on Retrieval Sec.14.2 Rocchio classifica<on   Rocchio forms a simple representa<on for each class: the centroid/prototype   Classifica<on is based on similarity to / distance from the prototype/centroid   It does not guarantee that classifica<ons are consistent with the given training data   It is lihle used outside text classifica<on   It has been used quite effec<vely for text classifica<on   But in general worse than Naïve Bayes   Again, cheap to train and test documents 14 7 Introduc)on to Informa)on Retrieval Sec.14.3 k Nearest Neighbor Classifica<on   kNN = k Nearest Neighbor           To classify a document d into class c: Define k ­neighborhood N as k nearest neighbors of d Count number of documents i in N that belong to c Es<mate P(c|d) as i/k Choose as class argmaxc P(c|d) [ = majority class] 15 Introduc)on to Informa)on Retrieval Sec.14.3 Example: k=6 (6NN) P(science| )? Government Science Arts 16 8 Introduc)on to Informa)on Retrieval Sec.14.3 Nearest ­Neighbor Learning Algorithm   Learning is just storing the representa<ons of the training examples in D.   Tes<ng instance x (under 1NN):   Compute similarity between x and all examples in D.   Assign x the category of the most similar example in D.   Does not explicitly compute a generaliza<on or category prototypes.   Also called:   Case ­based learning   Memory ­based learning   Lazy learning   Ra<onale of kNN: con<guity hypothesis 17 Introduc)on to Informa)on Retrieval Sec.14.3 kNN Is Close to Op<mal   Cover and Hart (1967)   Asympto<cally, the error rate of 1 ­nearest ­neighbor classifica<on is less than twice the Bayes rate [error rate of classifier knowing model that generated data]   In par<cular, asympto<c error rate is 0 if Bayes rate is 0.   Assume: query point coincides with a training point.   Both query point and training point contribute error → 2 <mes Bayes rate 18 9 Introduc)on to Informa)on Retrieval Sec.14.3 k Nearest Neighbor   Using only the closest example (1NN) to determine the class is subject to errors due to:   A single atypical example.   Noise (i.e., an error) in the category label of a single training example.   More robust alterna<ve is to find the k most ­similar examples and return the majority category of these k examples.   Value of k is typically odd to avoid <es; 3 and 5 are most common. 19 Introduc)on to Informa)on Retrieval Sec.14.3 kNN decision boundaries Boundaries are in principle arbitrary surfaces – but usually polyhedra Government Science Arts kNN gives locally defined decision boundaries between classes – far away points do not influence each classifica<on decision (unlike in Naïve Bayes, Rocchio, etc.) 20 10 Introduc)on to Informa)on Retrieval Sec.14.3 Similarity Metrics   Nearest neighbor method depends on a similarity (or distance) metric.   Simplest for con<nuous m ­dimensional instance space is Euclidean distance.   Simplest for m ­dimensional binary instance space is Hamming distance (number of feature values that differ).   For text, cosine similarity of d.idf weighted vectors is typically most effec<ve. 21 Introduc)on to Informa)on Retrieval Sec.14.3 Illustra<on of 3 Nearest Neighbor for Text Vector Space 22 11 Introduc)on to Informa)on Retrieval 3 Nearest Neighbor vs. Rocchio   Nearest Neighbor tends to handle polymorphic categories beher than Rocchio/NB. 23 Introduc)on to Informa)on Retrieval Sec.14.3 Nearest Neighbor with Inverted Index   Naively finding nearest neighbors requires a linear search through |D| documents in collec<on   But determining k nearest neighbors is the same as determining the k best retrievals using the test document as a query to a database of training documents.   Use standard vector space inverted index methods to find the k nearest neighbors.   Tes<ng Time: O(B|Vt|) where B is the average number of training documents in which a test ­document word appears.   Typically B << |D| 24 12 Introduc)on to Informa)on Retrieval Sec.14.3 kNN: Discussion   No feature selec<on necessary   Scales well with large number of classes   Don’t need to train n classifiers for n classes   Classes can influence each other   Small changes to one class can have ripple effect   Scores can be hard to convert to probabili<es   No training necessary   Actually: perhaps not true. (Data edi<ng, etc.)   May be expensive at test <me   In most cases it’s more accurate than NB or Rocchio 25 Introduc)on to Informa)on Retrieval Sec.14.6 kNN vs. Naive Bayes   Bias/Variance tradeoff   Variance ≈ Capacity   kNN has high variance and low bias.   Infinite memory   NB has low variance and high bias.   Decision surface has to be linear (hyperplane – see later)   Consider asking a botanist: Is an object a tree?   Too much capacity/variance, low bias   Botanist who memorizes   Will always say “no” to new object (e.g., different # of leaves)   Not enough capacity/variance, high bias   Lazy botanist   Says “yes” if the object is green   You want the middle ground (Example due to C. Burges) 26 13 Introduc)on to Informa)on Retrieval Sec.14.6 Bias vs. variance: Choosing the correct model capacity 27 Introduc)on to Informa)on Retrieval Sec.14.4 Linear classifiers and binary and mul<class classifica<on   Consider 2 class problems   Deciding between two classes, perhaps, government and non ­government   One ­versus ­rest classifica<on   How do we define (and find) the separa<ng surface?   How do we decide which region a test doc is in? 28 14 Introduc)on to Informa)on Retrieval Sec.14.4 Separa<on by Hyperplanes   A strong high ­bias assump<on is linear separability:   in 2 dimensions, can separate classes by a line   in higher dimensions, need hyperplanes   Can find separa<ng hyperplane by linear programming (or can itera<vely fit solu<on via perceptron):   separator can be expressed as ax + by = c 29 Introduc)on to Informa)on Retrieval Sec.14.4 Linear programming / Perceptron Find a,b,c, such that ax + by > c for red points ax + by < c for blue points. 30 15 Introduc)on to Informa)on Retrieval Sec.14.4 Which Hyperplane? In general, lots of possible solutions for a,b,c. 31 Introduc)on to Informa)on Retrieval Sec.14.4 Which Hyperplane?   Lots of possible solu<ons for a,b,c.   Some methods find a separa<ng hyperplane, but not the op<mal one [according to some criterion of expected goodness]   E.g., perceptron   Most methods find an op<mal separa<ng hyperplane   Which points should influence op<mality?   All points   Linear/logis<c regression   Naïve Bayes   Only “difficult points” close to decision boundary   Support vector machines 32 16 Introduc)on to Informa)on Retrieval Sec.14.4 Linear classifier: Example   Class: “interest” (as in interest rate)   Example features of a linear classifier   wi ti wi ti •  0.70 •  0.67 •  0.63 •  0.60 •  0.46 •  0.43 prime rate interest rates discount bundesbank •  −0.71 •  −0.35 •  −0.33 •  −0.25 •  −0.24 •  −0.24 dlrs world sees year group dlr   To classify, find dot product of feature vector and weights 33 Introduc)on to Informa)on Retrieval Sec.14.4 Linear Classifiers   Many common text classifiers are linear classifiers             Naïve Bayes Perceptron Rocchio Logis<c regression Support vector machines (with linear kernel) Linear regression with threshold   Despite this similarity, no<ceable performance differences   For separable problems, there is an infinite number of separa<ng hyperplanes. Which one do you choose?   What to do for non ­separable problems?   Different training methods pick different hyperplanes   Classifiers more powerful than linear o{en don’t perform beher on text problems. Why? 34 17 Introduc)on to Informa)on Retrieval Sec.14.2 Two ­class Rocchio as a linear classifier   Line or hyperplane defined by:   For Rocchio, set: [Aside for ML/stats people: Rocchio classifica<on is a simplifica<on of the classic Fisher Linear Discriminant where you don’t model the variance (or assume it is spherical).] 35 Introduc)on to Informa)on Retrieval Sec.14.2 Rocchio is a linear classifier 36 18 Introduc)on to Informa)on Retrieval Sec.14.4 Naive Bayes is a linear classifier   Two ­class Naive Bayes. We compute:   Decide class C if the odds is greater than 1, i.e., if the log odds is greater than 0.   So decision boundary is hyperplane: 37 Introduc)on to Informa)on Retrieval Sec.14.4 A nonlinear problem   A linear classifier like Naïve Bayes does badly on this task   kNN will do very well (assuming enough training data) 38 19 Introduc)on to Informa)on Retrieval Sec.14.4 High Dimensional Data   Pictures like the one at right are absolutely misleading!   Documents are zero along almost all axes   Most document pairs are very far apart (i.e., not strictly orthogonal, but only share very common words and a few scahered others)   In classifica<on terms: o{en document sets are separable, for most any classifica<on   This is part of why linear classifiers are quite successful in this domain 39 Introduc)on to Informa)on Retrieval Sec.14.5 More Than Two Classes   Any ­of or mul<value classifica<on         Classes are independent of each other. A document can belong to 0, 1, or >1 classes. Decompose into n binary problems Quite common for documents   One ­of or mul<nomial or polytomous classifica<on   Classes are mutually exclusive.   Each document belongs to exactly one class   E.g., digit recogni<on is polytomous classifica<on   Digits are mutually exclusive 40 20 Introduc)on to Informa)on Retrieval Sec.14.5 Set of Binary Classifiers: Any of   Build a separator between each class and its complementary set (docs from all other classes).   Given test doc, evaluate it for membership in each class.   Apply decision criterion of classifiers independently   Done   Though maybe you could do beher by considering dependencies between categories 41 Introduc)on to Informa)on Retrieval Sec.14.5 Set of Binary Classifiers: One of   Build a separator between each class and its complementary set (docs from all other classes).   Given test doc, evaluate it for membership in each class.   Assign document to class with:   maximum score   maximum confidence   maximum probability ? ? ?   Why different from mul<class/ any of classifica<on? 42 21 Introduc)on to Informa)on Retrieval Summary: Representa<on of Text Categoriza<on Ahributes   Representa<ons of text are usually very high dimensional (one feature for each word)   High ­bias algorithms that prevent overfi~ng in high ­ dimensional space should generally work best*   For most text categoriza<on tasks, there are many relevant features and many irrelevant ones   Methods that combine evidence from many or all features (e.g. naive Bayes, kNN) o{en tend to work beher than ones that try to isolate just a few relevant features* *Although the results are a bit more mixed than o{en thought 43 Introduc)on to Informa)on Retrieval Which classifier do I use for a given text classifica<on problem?   Is there a learning method that is op<mal for all text classifica<on problems?   No, because there is a tradeoff between bias and variance.   Factors to take into account:   How much training data is available?   How simple/complex is the problem? (linear vs. nonlinear decision boundary)   How noisy is the data?   How stable is the problem over <me?   For an unstable problem, it’s beher to use a simple and robust classifier. 44 22 Introduc)on to Informa)on Retrieval Ch. 14 Resources for today’s lecture   IIR 14   Fabrizio Sebas<ani. Machine Learning in Automated Text Categoriza<on. ACM Compu)ng Surveys, 34(1):1 ­47, 2002.   Yiming Yang & Xin Liu, A re ­examina<on of text categoriza<on methods. Proceedings of SIGIR, 1999.   Trevor Has<e, Robert Tibshirani and Jerome Friedman, Elements of Sta)s)cal Learning: Data Mining, Inference and Predic)on. Springer ­Verlag, New York.   Open Calais: Automa<c Seman<c Tagging   Free (but they can keep your data), provided by Thompson/Reuters   Weka: A data mining so{ware package that includes an implementa<on of many ML algorithms 45 23 ...
View Full Document

This note was uploaded on 01/21/2011 for the course CSCP 689 taught by Professor James during the Spring '10 term at Texas A&M.

Ask a homework question - tutors are online