Meaning of a word varies from one domain to another. Despite this important domain dependence in word semantics, existing word representation learning methods are bound to a single domain. Given a pair of source-target domains, we propose an unsupervised method for learning domain-specific word representations that accurately capture the domainspecific aspects of word semantics. First, we selec...

Transfer learning leverages the knowledge in one domain – the source domain – to improve learning efficiency in another domain – the target domain. Existing transfer learning research is relatively well-progressed, but only in situations where the feature spaces of the domains are homogeneous and the target domain contains at least a few labeled instances. However, transfer learning has not bee...

We report on experimental measurements of the growth of regular domains evolving from an irregular pattern in electroconvection. The late-time growth of the domains is consistent with the size of the domains scaling as t(n). We use two isotropic measurements of the domain size: the structure factor and the domain wall length. Measurements using the structure factor are consistent with t(1/5) gr...

Cross-domain learning targets at leveraging the knowledge from source domains to train accurate models for the test data from target domains with different but related data distributions. To tackle the challenge of data distribution difference in terms of raw features, previous works proposed to mine high-level concepts (e.g., word clusters) across data domains, which shows to be more appropria...

Abstract Transfer learning is a great technology that can leverage knowledge from label-rich domains to address problems in similar lack labeled data. Most previous works focus on single-source transfer, assuming the source domain contains sufficient data and close target domain. However, practical applications, this assumption hardly met, exist different domains. To improve adaptability of tra...

The histone chaperone FACT is an essential and abundant heterodimer found in all eukaryotes. Here we report a crystal structure of the middle domain of the large subunit of FACT (Spt16-M) to reveal a double pleckstrin homology architecture. This structure was found previously in the Pob3-M domain of the small subunit of FACT and in the related histone chaperone Rtt106, although Spt16-M is disti...

Sentiment classification aims to automatically predict sentiment polarity (e.g., positive or negative) of user generated sentiment data (e.g., reviews, blogs). Due to the mismatch among different domains, a sentiment classifier trained in one domain may not work well when directly applied to other domains. Thus, domain adaptation for sentiment classification algorithms are highly desirable to r...

In this paper we characterize the radical of an arbitrary‎ ‎submodule $N$ of a finitely generated free module $F$ over a‎ ‎commutatitve ring $R$ with identity‎. ‎Also we study submodules of‎ ‎$F$ which satisfy the radical formula‎. ‎Finally we derive‎ ‎necessary and sufficient conditions for $R$ to be a‎ ‎Pr$ddot{mbox{u}}$fer domain‎, ‎in terms of the radical of a‎ ‎cyclic submodule in $Rbigopl...

Hashing is widely applied to large-scale image retrieval due to the storage and retrieval efficiency. Existing work on deep hashing assumes that the database in the target domain is identically distributed with the training set in the source domain. This paper relaxes this assumption to a transfer retrieval setting, which allows the database and the training set to come from different but relev...