Results 1 - 10 of 719

Unlimited vocabulary speech recognition based on morphs discovered in an unsupervised manner

by Vesa Siivola, Teemu Hirsimäki, Mathias Creutz, Mikko Kurimo - in Proc. Eurospeech , 2003
"... We study continuous speech recognition based on sub-word units found in an unsupervised fashion. For agglutinative languages like Finnish, traditional word-based n-gram language modeling does not work well due to the huge number of different word forms. We use a method based on the Minimum Descripti ..."
Abstract - Cited by 71 (31 self) - Add to MetaCart
We study continuous speech recognition based on sub-word units found in an unsupervised fashion. For agglutinative languages like Finnish, traditional word-based n-gram language modeling does not work well due to the huge number of different word forms. We use a method based on the Minimum

Morphology-aware statistical machine translation based on morphs induced in an unsupervised manner

by Sami Virpioja, Jaakko J. Väyrynen, Mathias Creutz, Markus Sadeniemi - PROC. OF MT SUMMIT XI , 2007
"... In this paper, we apply a method of unsupervised morphology learning to a state-of-the-art phrase-based statistical machine translation (SMT) system. In SMT, words are traditionally used as the smallest units of translation. Such a system generalizes poorly to word forms that do not occur in the tra ..."
Abstract - Cited by 30 (7 self) - Add to MetaCart
In this paper, we apply a method of unsupervised morphology learning to a state-of-the-art phrase-based statistical machine translation (SMT) system. In SMT, words are traditionally used as the smallest units of translation. Such a system generalizes poorly to word forms that do not occur

Object class recognition by unsupervised scale-invariant learning

by R. Fergus, P. Perona, A. Zisserman - In CVPR , 2003
"... We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion and ..."
Abstract - Cited by 1127 (50 self) - Add to MetaCart
We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion

Unsupervised namedentity extraction from the web: An experimental study.

by Oren Etzioni , Michael Cafarella , Doug Downey , Ana-Maria Popescu , Tal Shaked , Stephen Soderland , Daniel S Weld , Alexander Yates - Artificial Intelligence, , 2005
"... Abstract 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 ..."
Abstract - Cited by 372 (39 self) - Add to MetaCart
Abstract 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

Information Retrieval as Statistical Translation

by Adam Berger, John Lafferty
"... We propose a new probabilistic approach to information retrieval based upon the ideas and methods of statistical machine translation. The central ingredient in this approach is a statistical model of how a user might distill or "translate" a given document into a query. To assess the rele ..."
Abstract - Cited by 313 (6 self) - Add to MetaCart
of the document-to-query translation process, and describe an algorithm for learning the parameters of this model in an unsupervised manner from a collection of documents. As we show, one can view this approach as a generalization and justification of the "language modeling" strategy recently proposed

Towards unsupervised pattern discovery in speech

by Alex S. Park, James R. Glass , 2008
"... We present a novel approach to speech processing based on the principle of pattern discovery. Our work represents a departure from traditional models of speech recognition, where the end goal is to classify speech into categories defined by a prespecified inventory of lexical units (i.e., phones or ..."
Abstract - Cited by 78 (10 self) - Add to MetaCart
or words). Instead, we attempt to discover such an inventory in an unsupervised manner by exploiting the structure of repeating patterns within the speech signal. We show how pattern discovery can be used to automatically acquire lexical entities directly from an untranscribed audio stream. Our approach

Inferring High-Level Behavior from Low-Level Sensors

by Donald J. Patterson, Lin Liao, Dieter Fox, Henry Kautz , 2003
"... We present a method of learning a Bayesian model of a traveler moving through an urban environment. This technique is novel in that it simultaneously learns a unified model of the traveler's current mode of transportation as well as his most likely route, in an unsupervised manner. The model ..."
Abstract - Cited by 200 (17 self) - Add to MetaCart
We present a method of learning a Bayesian model of a traveler moving through an urban environment. This technique is novel in that it simultaneously learns a unified model of the traveler's current mode of transportation as well as his most likely route, in an unsupervised manner

Robust Higher Order Potentials for Enforcing Label Consistency

by P. Kohli, L. Ladický, P. H. S. Torr , 2009
"... This paper proposes a novel framework for labelling problems which is able to combine multiple segmentations in a principled manner. Our method is based on higher order conditional random fields and uses potentials defined on sets of pixels (image segments) generated using unsupervised segmentation ..."
Abstract - Cited by 259 (34 self) - Add to MetaCart
This paper proposes a novel framework for labelling problems which is able to combine multiple segmentations in a principled manner. Our method is based on higher order conditional random fields and uses potentials defined on sets of pixels (image segments) generated using unsupervised segmentation

Unsupervised learning of shape manifolds

by Nasir Rajpoot, Muhammad Arif, Abhir Bhalerao - In Proceedings of the British Machine Vision Conference , 2007
"... Classical shape analysis methods use principal component analysis to reduce the dimensionality of shape spaces. The basic assumption behind these methods is that the subspace corresponding to the major modes of variation for a particular class of shapes is linearised. This may not necessarily be the ..."
Abstract - Cited by 8 (3 self) - Add to MetaCart
be the case in practice. In this paper, we present a novel method for extraction of the intrinsic parameters of multiple shape classes in an unsupervised manner. The proposed method is based on learning the global structure of shape manifolds using diffusion maps. We demonstrate that the method is effective

What is the Best Multi-Stage Architecture for Object Recognition?

by Kevin Jarrett, Koray Kavukcuoglu, Yann Lecun
"... In many recent object recognition systems, feature extraction stages are generally composed of a filter bank, a non-linear transformation, and some sort of feature pooling layer. Most systems use only one stage of feature extraction in which the filters are hard-wired, or two stages where the filter ..."
Abstract - Cited by 252 (22 self) - Add to MetaCart
the filters in one or both stages are learned in supervised or unsupervised mode. This paper addresses three questions: 1. How does the non-linearities that follow the filter banks influence the recognition accuracy? 2. does learning the filter banks in an unsupervised or supervised manner improve
Results 1 - 10 of 719