Embedding Hierarchical Structures for Venue Category Representation

Venue categories used in location-based social networks often exhibit a hierarchical structure, together with the category sequences derived from users’ check-ins. The two data modalities provide a wealth of information for us to capture the semantic relationships between those categories. To understand the venue semantics, existing methods usually embed venue categories into low-dimensional spaces by modeling the linear context (i.e., the positional neighbors of the given category) in check-in sequences. However, the hierarchical structure of venue categories, which inherently encodes the relationships between categories, is largely untapped. In this article, we propose a venue C ategory E mbedding M odel named Hier-CEM , which generates a latent representation for each venue category by embedding the Hier archical structure of categories and utilizing multiple types of context. Specifically, we investigate two kinds of hierarchical context based on any given venue category hierarchy and show how to model them together with the linear context collaboratively. We apply Hier-CEM to three tasks on two real check-in datasets collected from Foursquare. Experimental results show that Hier-CEM is better at capturing both semantic and sequential information inherent in venues than state-of-the-art embedding methods.

Reading the Romancero: A journey from the score to the sound with a non-professional choir

This case study focuses on the processes involved in co-constructing an interpretation of Mario Castelnuovo-Tedesco’s Romancero Gitano with a non-professional choir. Rehearsals began in April 2018 and culminated with a performance in June 2018. In order to develop an understanding of the individual and collective processes involved, data were generated through autoethnography and journaling. These texts tracked our regular weekly rehearsals, any extra individual practice, and the performance experience. Seven journals were subsequently compiled and analyzed together with my autoethnography. The findings show that the bulk of the writings focused on technical questions like correctly executing the information contained in the score, with significantly fewer references to other aspects of musical interpretation, such as timbre, or personal reflections regarding our perception of the music and our journey in learning and performing the work. Furthermore, the texts reveal a hierarchical structure within the choir, especially related to perceived levels of musical literacy and/or institutionalized knowledge. In this article, I discuss the various experiences relating to the process of co-constructing a musical interpretation, together with the potential of journaling to develop reflexive, conscious, and inclusive processes of collective musical development within the context of a non-professional choir.

IPC Prediction of Patent Documents Using Neural Network with Attention for Hierarchical Structure

International patent classifications (IPCs) are assigned to patent documents; however, since the procedure for assigning classifications is manually done by the patent examiner, it takes a lot of time and effort to select some IPCs from about 70,000 IPCs. Hence, some research has been conducted on patent classification with machine learning. However, patent documents are very voluminous, and learning with all the claims (the part describing the content of the patent) as input would run out of the necessary memory. Therefore, most of the existing methods learn by excluding some information, such as using only the first claim as input. In this study, we propose a model that considers the contents of all claims by extracting important information for input. We also propose a new decoder that considers the hierarchical structure of the IPC. Finally, we evaluate the model using an evaluation index that assumes the actual use of IPC selection for patent documents.

Research on maintenance method of relay protection state based on combination weight and gray relation

Relatively independent evaluation parameters are selected from many parameters through pedigree clustering.Learning the analytic hierarchy process (ahp) and entropy weight method can determine the weight, and at the same time to understand the error of the analytic hierarchy process (ahp) and entropy weight method is large, so the combination of the subjective and objective weight obtained by the two methods, using the improved entropy weight-ahp method to determine the weight. The improved weight calculation method has a clear hierarchical structure, which not only considers the influence of subjective and objective factors, but also makes full use of the weight information in the hierarchical structure. Considering the uncertainty of information, gray relation is adopted to deal with the data, so as to make maintenance rules.

LDH-derived phosphide/N-doped graphene oxide hierarchical electrocatalyst for enhanced oxygen evolution reaction

In this work, high efficient electrocatalyst Fe-Ni2P/N-GO with hierarchical structure was developed through phosphating NiFe-based layered double hydroxide (LDH) supported by N-doped graphene oxide (GO), which was assembled by the...