Replying to emails can be a daunting task especially if users are bombarded with hundreds of emails per day, or if they struggle with constructing well-formed socially acceptable replies. We present Awkwardly, a novel response suggester that generates top replies shown to a user in real-time. These short responses can be selected as a reply in a chat or email context. In this paper, we introduc...

The paper presents this year’s CUNI submissions to the WAT 2017 Translation Task focusing on the Japanese-English translation, namely Scientific papers subtask, Patents subtask and Newswire subtask. We compare two neural network architectures, the standard sequence-tosequence with attention (Seq2Seq) (Bahdanau et al., 2014) and an architecture using convolutional sentence encoder (FBConv2Seq) d...

With the development of smart power grids, electronic transformers have been widely used to monitor online status grids. However, drawback poor long-term stability, leading a requirement for frequent measurement. Aiming frequently and conveniently, we proposed an attention mechanism-optimized Seq2Seq network predict error state transformers, which combines mechanism, network, bidirectional long...

In this work, we present a compact, modular framework for constructing new recurrent neural architectures. Our basic module is a new generic unit, the Transition Based Recurrent Unit (TBRU). In addition to hidden layer activations, TBRUs have discrete state dynamics that allow network connections to be built dynamically as a function of intermediate activations. By connecting multiple TBRUs, we...

In the past few years, neural abstractive text summarization with sequence-to-sequence (seq2seq) models have gained a lot of popularity. Many interesting techniques been proposed to improve seq2seq models, making them capable handling different challenges, such as saliency, fluency and human readability, generate high-quality summaries. Generally speaking, most these differ in one three categor...

The sequence-to-sequence (Seq2Seq) model has been successfully applied to machine translation (MT). Recently, MT performances were improved by incorporating supervised attention into the model. In this paper, we introduce supervised attention to constituency parsing that can be regarded as another translation task. Evaluation results on the PTB corpus showed that the bracketing F-measure was im...

In this study, we present an infrastructure-independent multi-floor indoor localization scheme that uses a deep learning (DL)-based floor detection method and particle filter with clustering. To implement limited measurement data, incorporate the user’s vertical motion information to initialize optimize system. This assumes two prerequisites: capability for rapid extraction of features. These e...

Evolutionary optimization aims to tune the hyper-parameters during learning in a computationally fast manner. For of multi-task problems, evolution is done by creating unified search space with dimensionality that can include all tasks. Multi-task achieved via selective imitation where two individuals same type skill are encouraged crossover. Due relatedness tasks, resulting offspring may have ...

Abstract The tremendous amount of increase in the number documents available on Web has turned finding relevant piece information into a challenging, tedious, and time-consuming activity. Accordingly, automatic text summarization become an important field study by gaining significant attention from researchers. Lately, with advances deep learning, neural abstractive sequence-to-sequence (Seq2Se...