Biblio

Document-level relation extraction (RE) aims to extract relations among entities within a document, which is more complex than its sentence-level counterpart, especially in biomedical text mining. Chemical-disease relation (CDR) extraction aims to extract complex semantic relationships between chemicals and diseases entities in documents. In order to identify the relations within and across multiple sentences at the same time, existing methods try to build different document-level heterogeneous graph. However, the entity relation representations captured by these models do not make full use of the document information and disregard the noise introduced in the process of integrating various information. In this paper, we propose a novel model DAM-GAN to document-level biomedical RE, which can extract entity-level and mention-level representations of relation instances with R-GCN and Dual-Attention Multi-Instance Learning (DAM) respectively, and eliminate the noise with Generative Adversarial Network (GAN). Entity-level representations of relation instances model the semantic information of all entity pairs from the perspective of the whole document, while the mention-level representations from the perspective of mention pairs related to these entity pairs in different sentences. Therefore, entity- and mention-level representations can be better integrated to represent relation instances. Experimental results demonstrate that our model achieves superior performance on public document-level biomedical RE dataset BioCreative V Chemical Disease Relation(CDR).

This scientific paper reveals an intelligent system for data acquisition for dam monitoring and diagnose. This system is built around the RS485 communication standard and uses its own communication protocol [2]. The aim of the system is to monitor all signal levels inside the communication bus, respectively to detect the out of action data loggers. The diagnose test extracts the following functional parameters: supply voltage and the absolute value and common mode value for differential signals used in data transmission (denoted with “A” and “B”). Analyzing this acquired information, it's possible to find short-circuits or open-circuits across the communication bus. The measurement and signal processing functions, for flaws, are implemented inside the system's central processing unit. The next testing step is finding the out of action data loggers and is being made by trying to communicate with every data logger inside the network. The lack of any response from a data logger is interpreted as an error and using the code of the data logger's microcontroller, it is possible to find its exact position inside the dam infrastructure. The novelty of this procedure is the fact that it completely automates the diagnose procedure, which, until now, was made visually by checking every data logger.