This paper explores the effectiveness of parallel stylometric document embeddings in solving the authorship attribution task by testing a novel approach on literary texts in 7 different languages, totaling in 7051 unique 10,000-token chunks from 700 PoS and lemma annotated documents. We used these documents to produce four document embedding models using Stylo R package (word-based, lemma-based, PoS-trigrams-based, and PoS-mask-based) and one document embedding model using mBERT for each of the seven languages. We created further derivations of these embeddings in the form of average, product, minimum, maximum, and $l^2$ norm of these document embedding matrices and tested them both including and excluding the mBERT-based document embeddings for each language. Finally, we trained several perceptrons on the portions of the dataset in order to procure adequate weights for a weighted combination approach. We tested standalone (two baselines) and composite embeddings for classification accuracy, precision, recall, weighted-average, and macro-averaged $F_1$-score, compared them with one another and have found that for each language most of our composition methods outperform the baselines (with a couple of methods outperforming all baselines for all languages), with or without mBERT inputs, which are found to have no significant positive impact on the results of our methods.

Purpose Differentiated thyroid microcarcinoma (DTM) has a good prognosis and survival, but recurrent disease may appear during follow-up. The aim of this study was to evaluate the influence of initial treatment including surgery and radioactive iodine (¹³¹I) on the survival and recurrence in patients with DTM. Methods Between January 1979 and December 2006, 130 patients with DTM were retrospectively evaluated, with a median follow-up of 10 years. Total/near-total thyroidectomy was performed in 121 (93.1%) of 130 patients, followed with ¹³¹I ablation in 71 (54.6%) of 130 patients. Results The probability of disease-specific survival was 97.7% ± 1.3% after 5 and 10 years; the probability of disease-specific survival was 95.9% ± 2.2% after 15, 20, 25, and 28 years after the initial treatment and was significantly influenced by recurrence, clinical stage, and patients’ age (P = 0.0001, P = 0.0005, and P = 0.02, respectively). Sex, histopathological type of the tumor, metastases at presentation, initial treatment, performance of radioactive therapy, and risk categories had no influence on survival (P = 0.8, P = 0.6, P = 0.1, P = 0.4, P = 0.5, and P = 0.1, respectively). The overall recurrence rate was 10.8%, (6.9% in lymph nodes, 1.5% in thyroid bed, and 2.3% at distant sites), with a median appearance time of 30 months. Recurrences were significantly influenced by regional metastases at presentation, radioiodine ablation, and initial treatment (P = 0.0002, P = 0.005, and P = 0.003, respectively); there was no relationship based on age, sex, histological type of the tumor, and tumor multifocality. Conclusions To perform more accurate surveillance for recurrence, total/near-total thyroidectomy followed by radioiodine ablation may be the optimal initial treatment for patients with DTM.

Purpose: A hybrid approach is presented, which combines linguistic and statistical information to semi-automatically extract multiword term candidates from texts. Design/methodology/approach: The method is designed to be domain and language independent, focusing on languages with rich morphology. Here, it is used for extracting multiword terms from texts in Serbian, belonging to the agricultural engineering domain, as a use case. Predefined syntactic structures were used for multiword terms. For each structure, a finite state transducer was developed, which recognizes text sequences having that structure and outputs the sequence in a normalized form, so that different inflectional forms of the same multiword term can be counted properly. Term candidates were further filtered by their frequencies and evaluated by two domain experts. Findings: By using language resources, such as electronic dictionaries and grammars, 928 multiword terms were extracted out of 1,523 multiword terms that were recognized as candidates from a corpus having 42,260 different simple word forms; 870 of these were new, not already contained in the existing electronic dictionary of compounds for Serbian, and they were used to enrich the dictionary. Originality/value: The paper presents methodology that can significantly contribute to the development of terminology lexicons in different areas. In this particular use case, some important agricultural engineering concepts were extracted from the text, but this approach could be used for other domains and languages as well.

This paper presents the development of a WebGIS application aimed at providing safe and reliable data needed for reclamation of abandoned mines in national parks and other protected areas in Vojvodina in compliance with existing legal regulations. The geodatabase model for this application has been developed using UML and the CASE tool Microsoft Visio featuring an interface with ArcGIS. The WebGIS application was developed using GeoServer, an open source tool in the Java programming language, with integrated PostgreSQL DB and the possibility of generating and publishing WMS, WFS and KML services. The WebGIS application is publicly available, based on an appropriate central database, which for the first time encompasses all available data on abandoned mines in Vojvodina, and as such may serve as a model for similar databases on the territory of the Republic of Serbia.