Celebrated Sequence to Sequence learning (Seq2Seq) and its fruitful variants are powerful models to achieve excellent performance on the tasks that map sequences to sequences. However, these are many machine learning tasks with inputs naturally represented in a form of graphs, which imposes significant challenges to existing Seq2Seq models for lossless conversion from its graph form to the sequ...

The service quality of the subbase may affect overall road performance during its life. Thus, monitoring and prediction strain development are great importance for civil engineers. In this paper, a method based on time-series augmentation was employed to predict development. generative adversarial network (TimeGAN) model implemented perform data original monitored data. augmented trained throug...

The study on human-computer conversation systems is a hot research topic nowadays. One of the prevailing methods to build the system is using the generative Sequence-to-Sequence (Seq2Seq) model through neural networks. However, the standard Seq2Seq model is prone to generate trivial responses. In this paper, we aim to generate a more meaningful and informative reply when answering a given quest...

Neural conversation systems, typically using sequence-to-sequence (seq2seq) models, are showing promising progress recently. However, traditional seq2seq suffer from a severe weakness: during beam search decoding, they tend to rank universal replies at the top of the candidate list, resulting in the lack of diversity among candidate replies. Maximum Marginal Relevance (MMR) is a ranking algorit...

Chatbot is a growing topic, we built a open domain generative chatbot using seq2seq model with different machine learning framework (Tensorflow, MXNet). Our result show although seq2seq is a successful method in neural machine translation, use it solely on single turn chatbot yield pretty unsatisfactory result. Also existing free dialog corpus lacks both quality and quantity. Our conclusion it’...

Fraud in healthcare is widespread, as doctors could prescribe unnecessary treatments to increase bills. Insurance companies want detect these anomalous fraudulent bills and reduce their losses. Traditional fraud detection methods use expert rules manual data processing. Recently, machine learning techniques automate this process, but hand-labeled extremely costly usually out of date. We propose...

Despite much success in many large-scale language tasks, sequence-to-sequence (seq2seq) models have not been an ideal choice for conversational modeling as they tend to generate generic and repetitive responses. In this paper, we propose a Latent Topic Conversational Model (LTCM) that augments the seq2seq model with a neural topic component to better model human-human conversations. The neural ...

In this work, we introduce temporal hierarchies to the sequence to sequence (seq2seq) model to tackle the problem of abstractive summarization of scientific articles. The proposed Multiple Timescale model of the Gated Recurrent Unit (MTGRU) is implemented in the encoderdecoder setting to better deal with the presence of multiple compositionalities in larger texts. The proposed model is compared...

Question-answering chatbots have tremendous potential to complement humans in various fields. They are implemented using either rule-based or machine learning-based systems. Unlike the former, more scalable. Sequence-to-sequence (Seq2Seq) learning is one of most popular approaches and has shown remarkable progress since its introduction 2014. However, based on Seq2Seq show a weakness that it te...

Abstract Dynamic resource allocation and auto-scaling represent effective solutions for many cloud challenges, such as over-provisioning (i.e., energy-wasting, Service level Agreement “SLA” violation) under-provisioning Quality of “QoS” dropping) resources. Early workload prediction techniques play an important role in the success these solutions. Unfortunately, no technique is perfect suitable...