. This paper shows that the accuracy of learned text classifiers can be improved by augmenting a small number of labeled training documents with a large pool of unlabeled documents. This is important because in many text classification problems obtaining training labels is expensive, while large quantities of unlabeled documents are readily available. We introduce an algorithm for learning from labeled and unlabeled documents based on the combination of Expectation-Maximization (EM) and a naive Bayes classifier. The algorithm first trains a classifier using the available labeled documents, and probabilistically labels the unlabeled documents. It then trains a new classifier using the labels for all the documents, and iterates to convergence. This basic EM procedure works well when the data conform to the generative assumptions of the model. However these assumptions are often violated in practice, and poor performance can result. We present two extensions to the algorithm that improve ...

This paper introduces Transductive Support Vector Machines (TSVMs) for text classification. While regular Support Vector Machines (SVMs) try to induce a general decision function for a learning task, Transductive Support Vector Machines take into account a particular test set and try to minimize misclassifications of just those particular examples. The paper presents an analysis of why TSVMs are well suited for text classification. These theoretical findings are supported by experiments on three test collections. The experiments show substantial improvements over inductive methods, especially for small training sets, cutting the number of labeled training examples down to a twentieth on some tasks. This work also proposes an algorithm for training TSVMs efficiently, handling 10,000 examples and more.

This paper discusses the use of unlabeled examples for the problem of named entity classification. A large number of rules is needed for coverage of the domain, suggesting that a fairly large number of labeled examples should be required to train a classifier. However, we show that the use of unlabeled data can reduce the requirements for supervision to just 7 simple “seed ” rules. The approach gains leverage from natural redundancy in the data: for many named-entity instances both the spelling of the name and the context in which it appears are sufficient to determine its type. We present two algorithms. The first method uses a similar algorithm to that of (Yarowsky 95), with modifications motivated by (Blum and Mitchell 98). The second algorithm extends ideas from boosting algorithms, designed for supervised learning tasks, to the framework suggested by (Blum and Mitchell 98). 1

The World Wide Web is a vast source of information accessible to computers, but understandable only to humans. The goal of the research described here is to automatically create a computer understandable world wide knowledge base whose content mirrors that of the World Wide Web. Such a

Text documents often contain valuable structured data that is hidden in regular English sentences. This data is best exploited if available as a relational table that we could use for answering precise queries or for running data mining tasks. We explore a technique for extracting such tables from document collections that requires only a handful of training examples from users. These examples are used to generate extraction patterns, that in turn result in new tuples being extracted from the document collection. We build on this idea and present our Snowball system. Snowball introduces novel strategies for generating patterns and extracting tuples from plain-text documents. At each iteration of the extraction process, Snowball evaluates the quality of these patterns and tuples without human intervention, and keeps only the most reliable ones for the next iteration. In this paper we also develop a scalable evaluation methodology and metrics for our task, and present a t...

We review the literature on semi-supervised learning, which is an area in machine learning and more generally, artificial intelligence. There has been a whole spectrum of interesting ideas on how to learn from both labeled and unlabeled data, i.e. semi-supervised learning. This document is a chapter excerpt from the author’s doctoral thesis (Zhu, 2005). However the author plans to update the online version frequently to incorporate the latest development in the field. Please obtain the latest version at http://www.cs.wisc.edu/~jerryzhu/pub/ssl_survey.pdf

Information extraction systems usually require two dictionaries: a semantic lexicon containing domainspecific phrases and a dictionary of extraction patterns for the domain. We present a multi-level bootstrapping algorithm for building both the semantic lexicon and extraction patterns simultaneously. As input, our technique requires only unannotated training texts and a handful of "seed words" for a category. We use a "mutual bootstrapping" technique to alternately select the best extraction pattern for the category and bootstrap its extractions into the semantic lexicon, which is the basis for selecting the next extraction pattern. To make this approach more robust, we add a second level of bootstrapping ("meta-bootstrapping") that retains only the most reliable lexicon entries produced by mutual bootstrapping and then restarts the process. We evaluated this multi-level bootstrapping technique on a collection of corporate web pages and a corpus of terrorism news articles. The algorithm produced high-quality dictionaries for several semantic categories.

This article describes the software architecture of an autonomous, interactive tour-guide robot. It presents a modular and distributed software architecture, which integrates localization, mapping, collision avoidance, planning, and various modules concerned with user interaction and Web-based telepresence. At its heart, the software approach relies on probabilistic computation, on-line learning, and any-time algorithms. It enables robots to operate safely, reliably, and at high speeds in highly dynamic environments, and does not require any modifications of the environment to aid the robot's operation. Special emphasis is placed on the design of interactive capabilities that appeal to people's intuition. The interface provides new means for human-robot interaction with crowds of people in public places, and it also provides people all around the world with the ability to establish a "virtual telepresence" using the Web. To illustrate our approach, results are reported obtained in mid-...

The KNOWITALL system aims to automate the tedious process of extracting large collections of facts (e.g., names of scientists or politicians) from the Web in an unsupervised, domain-independent, and scalable manner. The paper presents an overview of KNOW-ITALL’s novel architecture and design principles, emphasizing its distinctive ability to extract information without any hand-labeled training examples. In its first major run, KNOW-ITALL extracted over 50,000 facts, but suggested a challenge: How can we improve KNOW-ITALL’s recall and extraction rate without sacrificing precision? This paper presents three distinct ways to address this challenge and evaluates their performance. Pattern Learning learns domain-specific extraction rules, which enable additional extractions. Subclass Extraction automatically identifies sub-classes in order to boost recall. List Extraction locates lists of class instances, learns a “wrapper ” for each list, and extracts elements of each list. Since each method bootstraps from KNOWITALL’s domainindependent methods, the methods also obviate hand-labeled training examples. The paper reports on experiments, focused on named-entity extraction, that measure the relative efficacy of each method and demonstrate their synergy. In concert, our methods gave KNOW-ITALL a 4-fold to 8-fold increase in recall, while maintaining high precision, and discovered over 10,000 cities missing from the Tipster Gazetteer.

Many application domains suffer from not having enough labeled training data for learning. However, large amounts of unlabeled examples can often be gathered cheaply. As a result, there has been a great deal of work in recent years on how unlabeled data can be used to aid classification. We consider an algorithm based on finding minimum cuts in graphs, that uses pairwise relationships among the examples in order to learn from both labeled and unlabeled data. Our algorithm