In recent years, with the rapid development of Internet technology, online shopping has become a mainstream way for users to purchase and consume. Sentiment analysis of a large number of user reviews on e-commerce platforms can effectively improve user satisfaction. This paper proposes a new sentiment analysis model-SLCABG, which is based on the sentiment lexicon and combines Convolutional Neural Network (CNN) and attention-based Bidirectional Gated Recurrent Unit (BiGRU). In terms of methods, the SLCABG model combines the advantages of sentiment lexicon and deep learning technology, and overcomes the shortcomings of existing sentiment analysis model of product reviews. The SLCABG model combines the advantages of the sentiment lexicon and deep learning techniques. First, the sentiment lexicon is used to enhance the sentiment features in the reviews. Then the CNN and the Gated Recurrent Unit (GRU) network are used to extract the main sentiment features and context features in the reviews and use the attention mechanism to weight. And finally classify the weighted sentiment features. In terms of data, this paper crawls and cleans the real book evaluation of dangdang.com, a famous Chinese e-commerce website, for training and testing, all of which are based on Chinese. The scale of the data has reached 100000 orders of magnitude, which can be widely used in the field of Chinese sentiment analysis. The experimental results show that the model can effectively improve the performance of text sentiment analysis.

In the distributed computing framework of Spark, cross-node/rack data transfer produced by map tasks and reduce tasks are common problems resulting in performance degradation, such as prolonging of entire execution time and network congestion. To address these problems, this paper utilizes the bipartite graph modelling to propose an optimal locality-aware task scheduling algorithm. By considering global optimality, the algorithm can generate the optimal scheduling solution for both the map tasks and the reduce tasks for data locality. Because of the different communication modes, this paper uses a unified graph to model the map task scheduling and the reduce task scheduling respectively. Then, by calculating the communication cost matrix of tasks, we formulate an optimal task scheduling scheme to minimize overall communication cost and transform the problem as the well-known graph problem: minimum weighted bipartite matching (MWBM), which can be resolved by Kuhn-Munkres algorithm. In addition, this paper proposes a locality-aware executor allocation strategy to improve the data locality further. We implement our algorithm and strategy in Spark-2.4.1 and evaluate its performance using several representative micro-benchmarks, macro-benchmarks, and HiBench benchmark suite. The experimental results verify that by reducing the network traffic and access latency, the proposed algorithm can improve the job performance substantially compared to some other task scheduling algorithms.

Recent researches try to integrate word information into the character-based Chinese NER by modifying the structure of the standard BiLSTMCRF model. They follow the paradigm of explicitly modeling forward and backward sequences, adopting an LSTM variant that takes both characters and words as input for each direction. Though enriching the representations, these models cannot fully exploit the interaction between future and past contexts. In this paper, we propose a novel word-character graph convolution network (WC-GCN) which uses a cross GCN block to simultaneously process the word-character directed acyclic graphs (DAGs) of two directions. To improve the capture of long-distance dependency, a global attention GCN block is introduced to learn node representations conditioned on a global context. In both blocks, unlike previous works where each word is attached to its associated character or taken as a shortcut between LSTM cells, words and characters are treated equally as nodes in the graph and have their instance-specific representations. Experiments on four widely used datasets show that our proposed model can work standalone or with the standard BiLSTM. Both forms can outperform previous LSTM-based models without training on extra corpora while only an external lexicon and its corresponding pretrained character and word embeddings are needed.

As an important application of IoT (the Internet of Things) devices, sentiment analysis has been paid more attention with the rapid development of artificial intelligence. As a widely used method in artificial intelligence applications, traditional deep learning methods need massive data for training. However, due to the limitations of hardware, Internet of things devices have deficiencies in processing big data. In the case of insufficient sample size, how to carry out machine learning method for IOT devices has become a common concern of the industry. In order to perform sentiment analysis on text with few data samples from the IoT devices, we propose FSLM, which is an intelligent few-shot learning model based on Siamese networks. The FSLM model consists of two self-attention models with the same parameters, which are divided into two parts. First, for two input texts, a self-attention model is used to extract sentiment features, and then the Mahalanobis distance is adopted to measure the similarity between two feature vectors to determine whether they belong to the same category. The FSLM is tested on the ARSC (Amazon Review Sentiment Classification) dataset. The extensive experimental results on this dataset demonstrate that the FSLM model has better accuracy and robustness for text sentiment analysis than other main existing models with a small number of samples.

With the rapid development of Internet of Things Technology, speech recognition has been applied more and more widely. Chinese Speech Recognition is a complex process. In the process of speech-to-text conversion, due to the influence of dialect, environmental noise, and context, the accuracy of speech-to-text in multi-round dialogues and specific contexts is still not high. After the general speech recognition technology, the text after speech recognition can be detected and corrected in the specific context, which is helpful to improve the robustness of text comprehension and is a beneficial supplement to the speech recognition technology. In this paper, a text processing model after Chinese Speech Recognition is proposed, which combines a bidirectional long short-term memory (LSTM) network with a conditional random field (CRF) model. The task is divided into two stages: text error detection and text error correction. In this paper, a bidirectional long short-term memory (Bi-LSTM) network and conditional random field are used in two stages of text error detection and text error correction respectively. Through verification and system test on the SIGHAN 2013 Chinese Spelling Check (CSC) dataset, the experimental results show that the model can effectively improve the accuracy of text after speech recognition.

For the rapid growth computation requirements in big data and artificial intelligence area, CPU-GPU heterogeneous clusters can provide more powerful computing capacity compared to CPU clusters. The number of GPUs on single computing node is scalable, which greatly improves the computing capacity of the cluster under the condition of limited cluster size. However, there is a lack of the effective load-balancing scheduling model in multi-GPU hardware environment. This paper proposes AEML, an acceleration engine for multi-GPU load-balancing in distributed heterogeneous environment. AEML can effectively integrate GPUs into distributed processing framework and achieve great load-balance among multiple heterogeneous GPUs. We propose a heterogeneous task execution model based on multiple GPUs and multiple streams (MGMS), which can effectively balance the workload of multiple GPUs. MGMS model utilizes four core techniques: a fine-grained task mapping mechanism, a device resource unified management scheme, a novel resource-aware GPU task scheduling strategy and a feedback-based streams adjustment scheme. The implementation of AEML system is based on Spark 2.4.1 and NVIDIA CUDA 10.0. We comprehensively evaluate the performance of AEML with multiple typical benchmarks. Experimental results show that AEML can fully exploit the computing power of GPUs and achieve great load-balance among multiple heterogeneous GPUs.