Results 1  10
of
172
Wrapper Induction for Information Extraction
, 1997
"... The Internet presents numerous sources of useful informationtelephone directories, product catalogs, stock quotes, weather forecasts, etc. Recently, many systems have been built that automatically gather and manipulate such information on a user's behalf. However, these resources are usually form ..."
Abstract

Cited by 519 (30 self)
 Add to MetaCart
The Internet presents numerous sources of useful informationtelephone directories, product catalogs, stock quotes, weather forecasts, etc. Recently, many systems have been built that automatically gather and manipulate such information on a user's behalf. However, these resources are usually formatted for use by people (e.g., the relevant content is embedded in HTML pages), so extracting their content is difficult. Wrappers are often used for this purpose. A wrapper is a procedure for extracting a particular resource's content. Unfortunately, handcoding wrappers is tedious. We introduce wrapper induction, a technique for automatically constructing wrappers. Our techniques can be described in terms of three main contributions. First, we pose the problem of wrapper construction as one of inductive learn...
An analysis of Bayesian classifiers
 IN PROCEEDINGS OF THE TENTH NATIONAL CONFERENCE ON ARTI CIAL INTELLIGENCE
, 1992
"... In this paper we present anaveragecase analysis of the Bayesian classifier, a simple induction algorithm that fares remarkably well on many learning tasks. Our analysis assumes a monotone conjunctive target concept, and independent, noisefree Boolean attributes. We calculate the probability that t ..."
Abstract

Cited by 333 (17 self)
 Add to MetaCart
In this paper we present anaveragecase analysis of the Bayesian classifier, a simple induction algorithm that fares remarkably well on many learning tasks. Our analysis assumes a monotone conjunctive target concept, and independent, noisefree Boolean attributes. We calculate the probability that the algorithm will induce an arbitrary pair of concept descriptions and then use this to compute the probability of correct classification over the instance space. The analysis takes into account the number of training instances, the number of attributes, the distribution of these attributes, and the level of class noise. We also explore the behavioral implications of the analysis by presenting
Cryptographic Limitations on Learning Boolean Formulae and Finite Automata
 PROCEEDINGS OF THE TWENTYFIRST ANNUAL ACM SYMPOSIUM ON THEORY OF COMPUTING
, 1989
"... In this paper we prove the intractability of learning several classes of Boolean functions in the distributionfree model (also called the Probably Approximately Correct or PAC model) of learning from examples. These results are representation independent, in that they hold regardless of the syntact ..."
Abstract

Cited by 311 (16 self)
 Add to MetaCart
In this paper we prove the intractability of learning several classes of Boolean functions in the distributionfree model (also called the Probably Approximately Correct or PAC model) of learning from examples. These results are representation independent, in that they hold regardless of the syntactic form in which the learner chooses to represent its hypotheses. Our methods reduce the problems of cracking a number of wellknown publickey cryptosystems to the learning problems. We prove that a polynomialtime learning algorithm for Boolean formulae, deterministic finite automata or constantdepth threshold circuits would have dramatic consequences for cryptography and number theory: in particular, such an algorithm could be used to break the RSA cryptosystem, factor Blum integers (composite numbers equivalent to 3 modulo 4), and detect quadratic residues. The results hold even if the learning algorithm is only required to obtain a slight advantage in prediction over random guessing. The techniques used demonstrate an interesting duality between learning and cryptography. We also apply our results to obtain strong intractability results for approximating a generalization of graph coloring.
Efficient noisetolerant learning from statistical queries
 JOURNAL OF THE ACM
, 1998
"... In this paper, we study the problem of learning in the presence of classification noise in the probabilistic learning model of Valiant and its variants. In order to identify the class of “robust” learning algorithms in the most general way, we formalize a new but related model of learning from stat ..."
Abstract

Cited by 288 (6 self)
 Add to MetaCart
In this paper, we study the problem of learning in the presence of classification noise in the probabilistic learning model of Valiant and its variants. In order to identify the class of “robust” learning algorithms in the most general way, we formalize a new but related model of learning from statistical queries. Intuitively, in this model, a learning algorithm is forbidden to examine individual examples of the unknown target function, but is given access to an oracle providing estimates of probabilities over the sample space of random examples. One of our main results shows that any class of functions learnable from statistical queries is in fact learnable with classification noise in Valiant’s model, with a noise rate approaching the informationtheoretic barrier of 1/2. We then demonstrate the generality of the statistical query model, showing that practically every class learnable in Valiant’s model and its variants can also be learned in the new model (and thus can be learned in the presence of noise). A notable exception to this statement is the class of parity functions, which we prove is not learnable from statistical queries, and for which no noisetolerant algorithm is known.
Efficient Distributionfree Learning of Probabilistic Concepts
 Journal of Computer and System Sciences
, 1993
"... In this paper we investigate a new formal model of machine learning in which the concept (boolean function) to be learned may exhibit uncertain or probabilistic behaviorthus, the same input may sometimes be classified as a positive example and sometimes as a negative example. Such probabilistic c ..."
Abstract

Cited by 197 (8 self)
 Add to MetaCart
In this paper we investigate a new formal model of machine learning in which the concept (boolean function) to be learned may exhibit uncertain or probabilistic behaviorthus, the same input may sometimes be classified as a positive example and sometimes as a negative example. Such probabilistic concepts (or pconcepts) may arise in situations such as weather prediction, where the measured variables and their accuracy are insufficient to determine the outcome with certainty. We adopt from the Valiant model of learning [27] the demands that learning algorithms be efficient and general in the sense that they perform well for a wide class of pconcepts and for any distribution over the domain. In addition to giving many efficient algorithms for learning natural classes of pconcepts, we study and develop in detail an underlying theory of learning pconcepts. 1 Introduction Consider the following scenarios: A meteorologist is attempting to predict tomorrow's weather as accurately as pos...
Learning in the Presence of Malicious Errors
 SIAM Journal on Computing
, 1993
"... In this paper we study an extension of the distributionfree model of learning introduced by Valiant [23] (also known as the probably approximately correct or PAC model) that allows the presence of malicious errors in the examples given to a learning algorithm. Such errors are generated by an advers ..."
Abstract

Cited by 168 (12 self)
 Add to MetaCart
In this paper we study an extension of the distributionfree model of learning introduced by Valiant [23] (also known as the probably approximately correct or PAC model) that allows the presence of malicious errors in the examples given to a learning algorithm. Such errors are generated by an adversary with unbounded computational power and access to the entire history of the learning algorithm's computation. Thus, we study a worstcase model of errors. Our results include general methods for bounding the rate of error tolerable by any learning algorithm, efficient algorithms tolerating nontrivial rates of malicious errors, and equivalences between problems of learning with errors and standard combinatorial optimization problems. 1 Introduction In this paper, we study a practical extension to Valiant's distributionfree model of learning: the presence of errors (possibly maliciously generated by an adversary) in the sample data. The distributionfree model typically makes the idealize...
Enhancing Supervised Learning with Unlabeled Data
, 2000
"... In many practical learning scenarios, there is a small amount of labeled data along with a large pool of unlabeled data. Many supervised learning algorithms have been developed and extensively studied. We present a new "cotraining" strategy for using unlabeled data to improve the performance ..."
Abstract

Cited by 120 (0 self)
 Add to MetaCart
In many practical learning scenarios, there is a small amount of labeled data along with a large pool of unlabeled data. Many supervised learning algorithms have been developed and extensively studied. We present a new "cotraining" strategy for using unlabeled data to improve the performance of standard supervised learning algorithms. Unlike much of the prior work, such as the cotraining procedure of Blum and Mitchell (1998), we do not assume there are two redundant views both of which are sufficient for perfect classification. The only requirement our cotraining strategy places on each supervised learning algorithm is that its hypothesis partitions the example space into a set of equivalence classes (e.g. for a decision tree each leaf defines an equivalence class). We evaluate our cotraining strategy via experiments using data from the UCI repository. 1. Introduction In many practical learning scenarios, there is a small amount of labeled data along with a lar...
Noisetolerant learning, the parity problem, and the statistical query model
 J. ACM
"... We describe a slightly subexponential time algorithm for learning parity functions in the presence of random classification noise. This results in a polynomialtime algorithm for the case of parity functions that depend on only the first O(log n log log n) bits of input. This is the first known ins ..."
Abstract

Cited by 116 (2 self)
 Add to MetaCart
We describe a slightly subexponential time algorithm for learning parity functions in the presence of random classification noise. This results in a polynomialtime algorithm for the case of parity functions that depend on only the first O(log n log log n) bits of input. This is the first known instance of an efficient noisetolerant algorithm for a concept class that is provably not learnable in the Statistical Query model of Kearns [7]. Thus, we demonstrate that the set of problems learnable in the statistical query model is a strict subset of those problems learnable in the presence of noise in the PAC model. In codingtheory terms, what we give is a poly(n)time algorithm for decoding linear k × n codes in the presence of random noise for the case of k = clog n log log n for some c> 0. (The case of k O(log n) is trivial since one can just individually check each of the 2 k possible messages and choose the one that yields the closest codeword.) A natural extension of the statistical query model is to allow queries about statistical properties that involve ttuples of examples (as opposed to single examples). The second result of this paper is to show that any class of functions learnable (strongly or weakly) with twise queries for t = O(log n) is also weakly learnable with standard unary queries. Hence this natural extension to the statistical query model does not increase the set of weakly learnable functions. 1.
Learning polynomials with queries: The highly noisy case
, 1995
"... Given a function f mapping nvariate inputs from a finite Kearns et. al. [21] (see also [27, 28, 22]). In the setting of agfieldFintoF, we consider the task of reconstructing a list nostic learning, the learner is to make no assumptions regarding of allnvariate degreedpolynomials which agree withf ..."
Abstract

Cited by 87 (18 self)
 Add to MetaCart
Given a function f mapping nvariate inputs from a finite Kearns et. al. [21] (see also [27, 28, 22]). In the setting of agfieldFintoF, we consider the task of reconstructing a list nostic learning, the learner is to make no assumptions regarding of allnvariate degreedpolynomials which agree withfon a the natural phenomena underlying the input/output relationship tiny but nonnegligible fraction, , of the input space. We give a of the function, and the goal of the learner is to come up with a randomized algorithm for solving this task which accessesfas a simple explanation which best fits the examples. Therefore the black box and runs in time polynomial in1;nand exponential in best explanation may account for only part of the phenomena. d, provided is(pd=jFj). For the special case whend=1, In some situations, when the phenomena appears very irregular, we solve this problem for jFj>0. In this case the providing an explanation which fits only part of it is better than nothing. Interestingly, Kearns et. al. did not consider the use of running time of our algorithm is bounded by a polynomial queries (but rather examples drawn from an arbitrary distribuand exponential ind. Our algorithm generalizes a previously tion) as they were skeptical that queries could be of any help. known algorithm, due to Goldreich and Levin, that solves this We show that queries do seem to help (see below). task for the case whenF=GF(2)(andd=1).
A Theory of Learning Classification Rules
, 1992
"... The main contributions of this thesis are a Bayesian theory of learning classification rules, the unification and comparison of this theory with some previous theories of learning, and two extensive applications of the theory to the problems of learning class probability trees and bounding error whe ..."
Abstract

Cited by 79 (6 self)
 Add to MetaCart
The main contributions of this thesis are a Bayesian theory of learning classification rules, the unification and comparison of this theory with some previous theories of learning, and two extensive applications of the theory to the problems of learning class probability trees and bounding error when learning logical rules. The thesis is motivated by considering some current research issues in machine learning such as bias, overfitting and search, and considering the requirements placed on a learning system when it is used for knowledge acquisition. Basic Bayesian decision theory relevant to the problem of learning classification rules is reviewed, then a Bayesian framework for such learning is presented. The framework has three components: the hypothesis space, the learning protocol, and criteria for successful learning. Several learning protocols are analysed in detail: queries, logical, noisy, uncertain and positiveonly examples. The analysis is done by interpreting a protocol as a...