Most existing aspect-term level sentiment analysis (ATSA) approaches combined neural networks with attention mechanisms built upon given aspect to generate refined sentence representation for better predictions. In these methods, terms are always provided in both training and testing process which may degrade aspect-level into sentence-level prediction. However, the annotated term might be unav...

In this paper, we present our team TUT/NII results at DUC 2005 and additional experiments on improving multi-document summarization. Summarization systems have typically focused on the factual aspect of information needs. Subjectivity analysis is another essential aspect for better understanding of information needs. Our approach is based on sentence extraction, weighted by sentence type annota...

The expression of new aspect-oriented structures of the 23 GoF design patterns in term of a pivot meta-model that we propose for aspect-oriented modelling; proves strong similarities between most of the models that we obtained for these patterns. This work led us therefore to propose a new taxonomy of patterns and consequently to identify a new set of aspect-oriented design patterns. We propose...

The tourism sector in Indonesia experienced growth and made a positive contribution to the national economy, but this has yet reach its target. Therefore, government of implemented sustainable development program by establishing ten priority destinations. Aspect-based sentiment analysis (ABSA) towards tourist attraction reviews can assist developing potential goals. ABSA process compares with t...

Проведен анализ современного состояния и изменения за многолетний период характеристик зимнего гидрохимического режима Иваньковского водохранилища. Представлены осредненные с 2013 по 2019 гг. концентрации главных ионов биогенных элементов, значений минерализации воды, физико-химических показателей органического вещества, а также концентраций марганца в различные сезоны года. Показаны отличия во...

For the guided summarization task of TAC 2010, we submitted two runs using the combination of manifold ranking score and aspects information. The only difference between these two runs is that one computes a score according to aspect information while the other one considers aspect coverage in each sentence. For the update summarization task, we adopt similar methods and simultaneously penalize...