Learn More
In this paper we address the question of how to render sequence-level networks better at handling structured input. We propose a machine reading simulator which processes text incrementally from left to right and performs shallow reasoning with memory and attention. The reader extends the Long Short-Term Memory architecture with a memory network in place of(More)
Semantic parsing aims at mapping natural language to machine interpretable meaning representations. Traditional approaches rely on high-quality lexicons, manually-built templates, and linguistic features which are either domainor representation-specific. In this paper we present a general method based on an attention-enhanced encoder-decoder model. We(More)
Binding of the HIV envelope to the chemokine coreceptors triggers membrane fusion and signal transduction. The fusion process has been well characterized, yet the role of coreceptor signaling remains elusive. Here, we describe a critical function of the chemokine coreceptor signaling in facilitating HIV infection of resting CD4 T cells. We find that static(More)
This paper presents a method to discriminate pixel differences according to their impact toward perceived visual quality. Noticeable local contrast changes are formulated firstly since contrast is the basic sensory feature in the human visual system (HVS) perception. The analysis aims at quantifying the actual impact of such changes (further divided into(More)
We propose Adaptive Recursive Neural Network (AdaRNN) for target-dependent Twitter sentiment classification. AdaRNN adaptively propagates the sentiments of words to target depending on the context and syntactic relationships between them. It consists of more than one composition functions, and we model the adaptive sentiment propagations as distributions(More)
To accelerate the application of the CRISPR/Cas9 (clustered regularly interspaced short palindromic repeats/ CRISPR-associated protein 9) system to a variety of plant species, a toolkit with additional plant selectable markers, more gRNA modules, and easier methods for the assembly of one or more gRNA expression cassettes is required. We developed a(More)
Recent years have witnessed the explosive growth of online social media. Weibo, a Twitter-like online social network in China, has attracted more than 300 million users in less than three years, with more than 1000 tweets generated in every second. These tweets not only convey the factual information, but also reflect the emotional states of the authors,(More)
At low bit rates, better coding quality can be achieved by downsampling the image prior to compression and estimating the missing portion after decompression. This paper presents a new algorithm in such a paradigm, based on the adaptive decision of appropriate downsampling directions/ratios and quantization steps, in order to achieve higher coding quality(More)
Arabidopsis mutants produced by constitutive overexpression of the CRISPR/Cas9 genome editing system are usually mosaics in the T1 generation. In this study, we used egg cell-specific promoters to drive the expression of Cas9 and obtained non-mosaic T1 mutants for multiple target genes with high efficiency. Comparisons of 12 combinations of eight promoters(More)
The CTG repeat involved in myotonic dystrophy is one of the most unstable trinucleotide repeats. However, the molecular mechanisms underlying this particular form of genetic instability—biased towards expansions—have not yet been completely elucidated. We previously showed, with highly unstable CTG repeat arrays in DM1 transgenic mice, that Msh2 is required(More)