Adversarial Separation Network for Text Style Transfer

This article considers the task of text style transfer: transforming a specific style of sentence into another while preserving its style-independent content. A dominate approach to text style transfer is to learn a good content factor of text, define a fixed vector for every style and recombine them to generate text in the required style. In fact, there are a large number of different words to convey the same style from different aspects. Thus, using a fixed vector to represent one style is very inefficient, which causes the weak representation power of the style vector and limits text diversity of the same style. To address this problem, we propose a novel neural generative model called Adversarial Separation Network (ASN), which can learn the content and style vector jointly and the learnt vectors have strong representation power and good interpretabilities. In our method, adversarial learning is implemented to enhance our model’s capability of disentangling the two factors. To evaluate our method, we conduct experiments on two benchmark datasets. Experimental results show our method can perform style transfer better than strong comparison systems. We also demonstrate the strong interpretability of the learnt latent vectors.

MMPC-RF: A Deep Multimodal Feature-Level Fusion Architecture for Hybrid Spam E-mail Detection

Hybrid spam is an undesirable e-mail (electronic mail) that contains both image and text parts. It is more harmful and complex as compared to image-based and text-based spam e-mail. Thus, an efficient and intelligent approach is required to distinguish between spam and ham. To our knowledge, a small number of studies have been aimed at detecting hybrid spam e-mails. Most of these multimodal architectures adopted the decision-level fusion method, whereby the classification scores of each modality were concatenated and fed to another classification model to make a final decision. Unfortunately, this method not only demands many learning steps, but it also loses correlation in mixed feature space. In this paper, we propose a deep multimodal feature-level fusion architecture that concatenates two embedding vectors to have a strong representation of e-mails and increase the performance of the classification. The paragraph vector distributed bag of words (PV-DBOW) and the convolutional neural network (CNN) were used as feature extraction techniques for text and image parts, respectively, of the same e-mail. The extracted feature vectors were concatenated and fed to the random forest (RF) model to classify a hybrid e-mail as either spam or ham. The experiments were conducted on three hybrid datasets made using three publicly available corpora: Enron, Dredze, and TREC 2007. According to the obtained results, the proposed model provides a higher accuracy of 99.16% compared to recent state-of-the-art methods.

Attention-Based Deep Multiple Instances Learning For Classifying Circular RNA and Other Long Non-Coding RNA

Circular RNA (circRNA) is a distinguishable circular formed long non-coding RNA (lncRNA), which has specific roles in transcriptional regulation, multiple biological processes. The identification of circRNA from other lncRNA is necessary for relevant research. In this study, we designed attention-based multi-instance learning (MIL) network architecture, which can be fed with raw sequence, to learn the sparse features in sequences and accomplish the identification task for circRNAs. The model outperformed previously reported models. Following the effectiveness validation of the attention score by the handwritten digit dataset, the key sequence loci underlying circRNAs recognition were obtained based on the corresponding attention score. Moreover, the motif enrichment analysis of the extracted key sequences identified some of the key motifs for circRNA formation. In conclusion, we designed a deep learning network architecture suitable for gene sequence learning with sparse features and implemented to the circRNA identification, and the network has a strong representation capability with its indication of some key loci.

Attention-based deep multiple instances learning for classifying circular RNA and other long non-coding RNA

Circular RNA (circRNA) is a distinguishable circular formed long non-coding RNA (lncRNA), which has specific roles in transcriptional regulation, multiple biological processes. The identification of circRNA from other lncRNA is necessary for relevant research. In this study, we designed attention-based multi-instance learning (MIL) network architecture, which can be fed with raw sequence, to learn the sparse features in sequences and accomplish the identification task for circRNAs. The model outperformed previously reported models. Following the effectiveness validation of the attention score by the handwritten digit dataset, the key sequence loci underlying circRNAs recognition were obtained based on the corresponding attention score. Moreover, the motif enrichment analysis of the extracted key sequences identified some of the key motifs for circRNA formation. In conclusion, we designed a deep learning network architecture suitable for gene sequence learning with sparse features and implemented to the circRNA identification, and the network has a strong representation capability with its indication of some key loci.

Paradigmatic Relations Interact During the Production of Complex Words: Evidence From Variable Plurals in Dutch

A growing body of work in psycholinguistics suggests that morphological relations between word forms affect the processing of complex words. Previous studies have usually focused on a particular type of paradigmatic relation, for example the relation between paradigm members, or the relation between alternative forms filling a particular paradigm cell. However, potential interactions between different types of paradigmatic relations have remained relatively unexplored. This paper presents two corpus studies of variable plurals in Dutch to test hypotheses about potentially interacting paradigmatic effects. The first study shows that generalization across noun paradigms predicts the distribution of plural variants, and that this effect is diminished for paradigms in which the plural variants are more likely to have a strong representation in the mental lexicon. The second study demonstrates that the pronunciation of a target plural variant is affected by coactivation of the alternative variant, resulting in shorter segmental durations. This effect is dependent on the representational strength of the alternative plural variant. In sum, by exploring interactions between different types of paradigmatic relations, this paper provides evidence that storage of morphologically complex words may affect the role of generalization and coactivation during production.

DISEASE INVESTIGATION OF STONE CARVING BY SPATIAL ANALYSIS: A CASE STUDY ON THE STONE CARVING OF DAZU THOUSAND-HAND BODHISATTVA

Cultural relics are often threatened by nature and human, especially stone carving relics which have immovable characteristics. Compared with other cultural relics, the diseases of stone carving relics are more complex, and they can affect carvings’ cultural and artistic value to a great extent. This article selects Dazu thousand-hand bodhisattva as a case, not only because it has a strong representation in Chinese stone carving art, but also considering that there are many complex diseases in the whole range after a long history, therefore the Dazu thousand-hand bodhisattva has high research value, and scientific investigation methods are essential for the protection and research of cultural relics. The main purpose of this paper is to investigate the arm diseases of Dazu thousand-hand bodhisattva by using the two methods of GIS spatial analysis: kernel density analysis and trend analysis. The past investigation methods are difficult to achieve the expected results because of their strong subjectivity and narrow range, and the use of spatial analysis to investigate the diseases of stone carvings can study the spatial characteristics and coupling relationship of stone carvings from the macro level.

Cross-domain Recommendation with Bridge-Item Embeddings

Web systems that provide the same functionality usually share a certain amount of items. This makes it possible to combine data from different websites to improve recommendation quality, known as the cross-domain recommendation task. Despite many research efforts on this task, the main drawback is that they largely assume the data of different systems can be fully shared . Such an assumption is unrealistic different systems are typically operated by different companies, and it may violate business privacy policy to directly share user behavior data since it is highly sensitive. In this work, we consider a more practical scenario to perform cross-domain recommendation. To avoid the leak of user privacy during the data sharing process, we consider sharing only the information of the item side, rather than user behavior data. Specifically, we transfer the item embeddings across domains, making it easier for two companies to reach a consensus (e.g., legal policy) on data sharing since the data to be shared is user-irrelevant and has no explicit semantics. To distill useful signals from transferred item embeddings, we rely on the strong representation power of neural networks and develop a new method named as NATR (short for N eural A ttentive T ransfer R ecommendation ). We perform extensive experiments on two real-world datasets, demonstrating that NATR achieves similar or even better performance than traditional cross-domain recommendation methods that directly share user-relevant data. Further insights are provided on the efficacy of NATR in using the transferred item embeddings to alleviate the data sparsity issue.

Tieslietu padomes lēmumu efektivitāte

The question of effectiveness of Judicial Council’s decisions becomes topical in period of voiced disagreements among state powers. European type of Judicial Councils is designed to give strong representation to judiciary’s voice, however for any state power to be fully effective they need to conduct a dialogue and cooperate among themselves. The article looks at several recent examples of overlapping competencies, paying particular attention to the newly and controversially established Economic Affairs Court. The status of Judicial Council’s decisions in Latvian legal system is addressed, as well.

Kambilangatao: A Study of the Visual Grammar of Tarpaulins

The overwhelming number of tarpaulins posted in strategic places around the Meranaw communities in Marawi City, Philippines, have tagged the City as the “City of Tarpaulins”. For years, tarpaulins have been invading streets and walls. This multimedia landscape is not only a powerful product of the digitalized world but is also a strong representation of the modernizing Meranaw culture. This study ventured into analyzing the texts and photographs presented in the tarpaulins to better understand the contemporary concept of Kambilangatao or the Meranaw values of becoming a good person.Through the analysis, the study shows that the Meranaw in the contemporary era has evolved into a new identity. The study has brought out the 5k concepts of Meranaw values that make up Kambilangatao or the art of becoming a good person in thoughts, deeds, and actions, such as kapamagogopa or helping one another, kapamagawida or mutual support, kapamagadata or respect for one another, kaseselai or honoring one another, and kambangsa or pride in the family lineage. Through the tarpaulins a visage of the contemporary Meranaw is revealed. The visual grammar of the tarpaulins reveals that the contemporary bilangatao or an ideal person is described as a degree holder, achiever, confident, religious, honorable, and a good leader.