This paper investigates adapting a lexicalized probabilistic context-free grammar (PCFG) to a novel domain, using maximum a posteriori (MAP) estimation. The MAP framework is general enough to include some previous model adaptation approaches, such as corpus mixing in Gildea (2001), for example. Other approaches falling within this framework are more effective. In contrast to the results in Gild...

Abstract Image-based fruit classification offers many useful applications in industrial production and daily life, such as self-checkout the supermarket, automatic sorting dietary guidance. However, task will have different data distributions due to application scenarios. One feasible solution solve this problem is use domain adaptation that adapts knowledge from original training (source domai...

In real-life conditions, mismatch between development and test domain degrades speaker recognition performance. To solve the issue, many researchers explored domain adaptation approaches using matched in-domain dataset. However, adaptation would be not effective if the dataset is insufficient to estimate channel variability of the domain. In this paper, we explore the problem of performance deg...

The transfer learning method, based on unsupervised domain adaptation (UDA), has been broadly utilized in research fault diagnosis under variable working conditions with certain results. However, traditional UDA methods pay more attention to extracting information for the class labels and of data, ignoring influence data structure extracted features. Therefore, we propose a domain-adversarial m...

Domain adaptation aims at learning robust classifiers across domains using labeled data from a source domain. Representation learning methods, which project the original features to a new feature space, have been proved to be quite effective for this task. However, these unsupervised methods neglect the domain information of the input and are not specialized for the classification task. In this...

Domain adaptation, and transfer learning more generally, seeks to remedy the problem created when training and testing datasets are generated by different distributions. In this work, we introduce a new unsupervised domain adaptation algorithm for when there are multiple sources available to a learner. Our technique assigns a rough labeling on the target samples, then uses it to learn a transfo...

We present two Twitter datasets annotated with coarse-grained word senses (supersenses), as well as a series of experiments with three learning scenarios for supersense tagging: weakly supervised learning, as well as unsupervised and supervised domain adaptation. We show that (a) off-the-shelf tools perform poorly on Twitter, (b) models augmented with embeddings learned from Twitter data perfor...

This paper addresses speaker verification domain adaptation with inadequate in-domain data. Specifically, we explore the cases where in-domain data sets do not include speaker labels, contain speakers with few samples, or contain speakers with low channel diversity. Existing domain adaptation methods are reviewed, and their shortcomings are discussed. We derive an unsupervised version of fully ...

This paper investigates unsupervised language model adaptation, from ASR transcripts. N-gram counts from these transcripts can be used either to adapt an existing n-gram model or to build an n-gram model from scratch. Various experimental results are reported on a particular domain adaptation task, namely building a customer care application starting from a general voicemail transcription syste...

Topic models, an unsupervised technique for inferring translation domains improve machine translation quality. However, previous work uses only the source language and completely ignores the target language, which can disambiguate domains. We propose new polylingual tree-based topic models to extract domain knowledge that considers both source and target languages and derive three different inf...