Topic modeling has been an increasingly mature method to bridge the semantic gap between the low-level features and high-level semantic information. However, with more and more high spatial resolution (HSR) images to deal with, conventional probabilistic topic model (PTM) usually presents the images with a dense semantic representation. This consumes more time and requires more storage space. I...

Current distributed representations of words show little resemblance to theories of lexical semantics. The former are dense and uninterpretable, the latter largely based on familiar, discrete classes (e.g., supersenses) and relations (e.g., synonymy and hypernymy). We propose methods that transform word vectors into sparse (and optionally binary) vectors. The resulting representations are more ...

Sentence-level classification and sequential labeling are two fundamental tasks in language understanding. While these two tasks are usually modeled separately, in reality, they are often correlated, for example in intent classification and slot filling, or in topic classification and named-entity recognition. In order to utilize the potential benefits from their correlations, we propose a join...

Bilinear approximation of a matrix is a powerful paradigm of unsupervised learning. In some applications, however, there is a natural hierarchy of concepts that ought to be reflected in the unsupervised analysis. For example, in the neurosciences image sequence considered here, there are the semantic concepts of pixel → neuron→ assembly that should find their counterpart in the unsupervised ana...

We consider two approaches for sparse decomposition of polyphonic music: a timedomain approach based on shift-invariant waveforms, and a frequency-domain approach based on phase-invariant power spectra. When trained on an example of a MIDI-controlled acoustic piano recording, both methods produce dictionary vectors or sets of vectors which represent underlying notes, and produce component activ...

Sparse program representations allow inter-statement dependences to be represented explicitly, enabling dataaow analyzers to restrict the propagation of information to paths where it could potentially aaect the dataaow solution. This paper describes the use of a single sparse program representation , the value dependence graph, in both general and analysis-specic contexts, and demonstrates its ...

Data collected from nature is usually unlabeled, and it difficult to be used directly. This issue well addressed by crowdsourcing, which provides a reasonable way for effectively using these unlabeled data. Generally, workers in crowdsourcing tasks are not professionals, so hard obtain high-quality labels. To address this issue, robust sparse weighted classification algorithm proposed, try adju...