Learning disentangled representations of natural language is essential for many NLP tasks, e.g., conditional text generation, style transfer, personalized dialogue systems, etc. Similar problems have been studied extensively for other forms of data, such as images and videos. However, the discrete nature of natural language makes the disentangling of textual representations more challenging (e.g., the manipulation over the data space cannot be easily achieved). Inspired by information theory, we propose a novel method that effectively manifests disentangled representations of text, without any supervision on semantics. A new mutual information upper bound is derived and leveraged to measure dependence between style and content. By minimizing this upper bound, the proposed method induces style and content embeddings into two independent low-dimensional spaces. Experiments on both conditional text generation and text-style transfer demonstrate the high quality of our disentangled representation in terms of content and style preservation.

Network traffic classification aims to recognize different application or traffic types by analyzing received data packets. This paper presents a neural network model with deep and parallel network-in-network (NIN) structures for classifying encrypted network traffic. Comparing with standard convolutional neural networks (CNN), NIN adopts a micro network after each convolution layer to enhance local modeling. Besides, NIN utilizes a global average pooling instead of traditional fully connected layers before final classification, which reduces the number of model parameters significantly. In our proposed method, deep NIN models with multiple MLP convolutional layers are built to map fixed-length packet vectors towards application or traffic labels. Furthermore, a parallel decision strategy of building two subnetworks to process packet header and packet body separately is designed considering that they may carry different kinds of clues for classification. The results of our experiments on the "ISCX VPN-nonVPN" encrypted traffic dataset show that NIN models can achieve a better balance between classification accuracy and model complexity than conventional CNNs. The parallel decision strategy can further improve the accuracy of using single NIN model for encrypted network traffic classification. Finally, the test set F1 scores of 0.983 and 0.985 are achieved for traffic characterization and application identification respectively.INDEX TERMS Network traffic classification, convolutional neural network, network-in-network, data packet.

No abstract

Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems. The learned representations are generally assumed to be continuous and real-valued, giving rise to a large memory footprint and slow retrieval speed, which hinders their applicability to low-resource (memory and computation) platforms, such as mobile devices. In this paper, we propose four different strategies to transform continuous and generic sentence embeddings into a binarized form, while preserving their rich semantic information. The introduced methods are evaluated across a wide range of downstream tasks, where the binarized sentence embeddings are demonstrated to degrade performance by only about 2% relative to their continuous counterparts, while reducing the storage requirement by over 98%. Moreover, with the learned binary representations, the semantic relatedness of two sentences can be evaluated by simply calculating their Hamming distance, which is more computational efficient compared with the inner product operation between continuous embeddings. Detailed analysis and case study further validate the effectiveness of proposed methods.

Constituting highly informative network embeddings is an important tool for network analysis. It encodes network topology, along with other useful side information, into lowdimensional node-based feature representations that can be exploited by statistical modeling. This work focuses on learning contextaware network embeddings augmented with text data.We reformulate the networkembedding problem, and present two novel strategies to improve over traditional attention mechanisms: (i) a content-aware sparse attention module based on optimal transport, and (ii) a high-level attention parsing module. Our approach yields naturally sparse and self-normalized relational inference. It can capture long-term interactions between sequences, thus addressing the challenges faced by existing textual network embedding schemes. Extensive experiments are conducted to demonstrate our model can consistently outperform alternative state-of-the-art methods. arXiv:1906.01840v1 [cs.CL] 5 Jun 2019 Sebastian Ruder. 2016. On word embeddings -part 2: Approximating the softmax. http://ruder. io/word-embeddings-softmax/. . 2018. Improved semantic-aware network embedding with fine-grained word alignment. In EMNLP. Xiaofei Sun, Jiang Guo, Xiao Ding, and Ting Liu. 2016. A general framework for content-enhanced network representation learning. In arXiv preprint arXiv:1610.02906. . 2018. A fast proximal point method for Wasserstein distance. In arXiv:1802.04307. . 2015. Learning continuous word embedding with metadata for question retrieval in community question answering. In ACL.