State-of-the-art natural language processing systems rely on supervision in the form of
annotated data to learn competent models. These models are generally trained on data in a …

We propose an unsupervised deep convolutional coupling network for change detection
based on two heterogeneous images acquired by optical sensors and radars on different …

We present a novel technique for learning semantic representations, which extends the
distributional hypothesis to multilingual data and joint-space embeddings. Our models …

In this paper, we use the framework of neural machine translation to learn joint sentence
representations across six very different languages. Our aim is that a representation which is …

Common representation learning (CRL), wherein different descriptions (or views) of the data
are embedded in a common subspace, has been receiving a lot of attention recently. Two …

We learn a joint multilingual sentence embedding and use the distance between sentences
in different languages to filter noisy parallel data and to mine for parallel data in large news …

Average word embeddings are a common baseline for more sophisticated sentence
embedding techniques. However, they typically fall short of the performances of more …

Distributed representations of meaning are a natural way to encode covariance
relationships between words and phrases in NLP. By overcoming data sparsity problems, as …

The sentiment classification performance relies on high-quality sentiment resources.
However, these resources are imbalanced in different languages. Cross-language …

We present a probabilistic model that simultaneously learns alignments and distributed
representations for bilingual data. By marginalizing over word alignments the model …