This paper presents a cache-based dynamic adaptation technique for lexicalized probabilistic context-free-grammar (LPCFG). Expected counts from machine-parsed sentences of in-domain data are stored in a cache, which are combined with prior counts from hand-annotated parses of outof-domain data using maximum a posteriori (MAP) estimation. This adaptation is unsupervised, and dynamic with an adap...

Adaptation is a ubiquitous neural and psychological phenomenon, with a wealth of instantiations and implications. Although a basic form of plasticity, it has, bar some notable exceptions, attracted computational theory of only one main variety. In this paper, we study adaptation from the perspective of factor analysis, a paradigmatic technique of unsupervised learning. We use factor analysis to...

This paper presents a novel multi-task learningbased method for unsupervised domain adaptation. Specifically, the source and target domain classifiers are jointly learned by considering the geometry of target domain and the divergence between the source and target domains based on the concept of multi-task learning. Two novel algorithms are proposed upon the method using Regularized Least Squar...

In this work, we face the problem of unsupervised domain adaptation with a novel deep learning approach which leverages on our finding that entropy minimization is induced by the optimal alignment of second order statistics between source and target domains. We formally demonstrate this hypothesis and, aiming at achieving an optimal alignment in practical cases, we adopt a more principled strat...

Adaptation of Automatic Speech Recognition (ASR) systems to a new domain (channel, speaker, topic, etc.) remains a significant challenge, as often, only a limited amount of target domain data for adaptation of Acoustic Models (AMs) is available. However, unlike GMMs, to date, there has not been an established, efficient method for adapting current state-of-theart Convolutional Neural Network (C...

In this work the theoretical concepts of unsupervised acoustic model training and the application and evaluation of unsupervised training schemes are described. Experiments aiming at speaker adaptation via unsupervised training are conducted on the KIT lecture translator system. Evaluation takes place with respect to training e ciency and overall system performance in dependency of the availabl...

This paper investigates the unsupervised adaptation of an acoustic model to a domain with mismatched acoustic conditions. We use techniques borrowed from the unsupervised training literature to adapt an acoustic model trained on the Wall Street Journal corpus to the Aurora-2 domain, which is composed of read digit strings over a simulated noisy telephone channel. We show that it is possible to ...

The goal of domain adaptation is to adapt models learned on a source domain to a particular target domain. Most methods for unsupervised domain adaptation proposed in the literature to date, assume that the set of classes present in the target domain is identical to the set of classes present in the source domain. This is a restrictive assumption that limits the practical applicability of unsup...

Person re-identification (re-ID) models trained on one domain often fail to generalize well to another. In our attempt, we present a “learning via translation” framework. In the baseline, we translate the labeled images from source to target domain in an unsupervised manner. We then train re-ID models with the translated images by supervised methods. Yet, being an essential part of this framewo...

In limited data domains, many effective language modeling techniques construct models with parameters to be estimated on an in-domain development set. However, in some domains, no such data exist beyond the unlabeled test corpus. In this work, we explore the iterative use of the recognition hypotheses for unsupervised parameter estimation. We also evaluate the effectiveness of supervised adapta...