A Sequential Algorithm for Training Text Classifiers

Lewis, David; Gale, William A.

doi:10.1007/978-1-4471-2099-5_1

Cited by 1,013 publications

(297 citation statements)

References 20 publications

Supporting

Mentioning

238

Contrasting

Unclassified

Order By: Relevance

“…The active learning literature have also proposed a variety of ways to choose which data should be labeled [1,12,17,18]. However, it has been shown that the frequency and repetition of questions can affect the accuracy and compliance with experience sampling [22].…”

Section: Related Workmentioning

confidence: 99%

Using Decision-Theoretic Experience Sampling to Build Personalized Mobile Phone Interruption Models

Rosenthal

Dey

Veloso

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We contribute a method for approximating users' interruptibility costs to use for experience sampling and validate the method in an application that learns when to automatically turn off and on the phone volume to avoid embarrassing phone interruptions. We demonstrate that users have varying costs associated with interruptions which indicates the need for personalized cost approximations. We compare different experience sampling techniques to learn users' volume preferences and show those that ask when our cost approximation is low reduce the number of embarrassing interruptions and result in more accurate volume classifiers when deployed for long-term use.

show abstract

Section: Related Workmentioning

confidence: 99%

Using Decision-Theoretic Experience Sampling to Build Personalized Mobile Phone Interruption Models

Rosenthal

Dey

Veloso

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Blum and Mitchell [16] provided the first formalization of learning in the multi-view framework, and proved that two independent, compatible views can be used to PAClearn [17], a concept based on few labeled and many unlabeled examples. At the meantime, they also introduced Co-Training, the first general-purpose, multiview algorithm.…”

Section: B Multiple Views Learningmentioning

confidence: 99%

“…SVSL, the most common active learning method, uses single classifier from one view to acquire the hypothesis. Such as the uncertainty sampling approach [17] and EM [19] belong to SVSL. Combination of SVSL and CoTraining, each of multi-views adopts one classifier to sampling, that is MVSL.…”

Section: B Multiple Views Learningmentioning

confidence: 99%

Multiple-View Active Learning for Environmental Sound Classification

Zhang

Lv²,

Zhao³

2016

Int. J. Onl. Eng.

View full text Add to dashboard Cite

“…For each combination of independent variables, we record: LGF performance metric proposed by Lewis and Gale [5], assume equal weights for recall and precision.…”

Section: Performance Evaluationmentioning

confidence: 99%

Adaptive Lightweight Text Filtering

Somlo

Howe

2001

Advances in Intelligent Data Analysis

View full text Add to dashboard Cite

Abstract. We present a lightweight text filtering algorithm intended for use with personal Web information agents. Fast response and low resource usage were the key design criteria, in order to allow the algorithm to run on the client side. The algorithm learns adaptive queries and dissemination thresholds for each topic of interest in its user profile. We describe a factorial experiment used to test the robustness of the algorithm under different learning parameters and more importantly, under limited training feedback. The experiment borrows from standard practice in TREC by using TREC-5 data to simulate a user reading and categorizing documents. Results indicate that the algorithm is capable of achieving good filtering performance, even with little user feedback.

show abstract

A Sequential Algorithm for Training Text Classifiers

Cited by 1,013 publications

References 20 publications

Using Decision-Theoretic Experience Sampling to Build Personalized Mobile Phone Interruption Models

Using Decision-Theoretic Experience Sampling to Build Personalized Mobile Phone Interruption Models

Multiple-View Active Learning for Environmental Sound Classification

Adaptive Lightweight Text Filtering

Contact Info

Product

Resources

About