Aspect term extraction is one of the important subtasks in aspect-based sentiment analysis. Previous studies have shown that using dependency tree structure representation is promising for this task. However, most dependency tree structures involve only one directional propagation on the dependency tree. In this paper, we first propose a novel bidirectional dependency tree network to extract dependency structure features from the given sentences. The key idea is to explicitly incorporate both representations gained separately from the bottom-up and top-down propagation on the given dependency syntactic tree. An end-to-end framework is then developed to integrate the embedded representations and BiLSTM plus CRF to learn both tree-structured and sequential features to solve the aspect term extraction problem. Experimental results demonstrate that the proposed model outperforms state-of-the-art baseline models on four benchmark SemEval datasets.

Algorithms to topically cluster and classify texts rely on information about their semantic distances and similarities. Standard methods based on the bag-of-words model to determine this information return only rough estimations regarding the relatedness of texts. Moreover, they are per se unable to find generalising terms or abstractions describing the textual contents. A new method to determine centroid terms in texts and to evaluate their similarity using those representing terms will be introduced. In first experiments, its results and advantages will be discussed.

Portfolio selection is a vital research field in modern finance. Multi-objective portfolio optimization problem is the portfolio selection process that results in the highest expected return rate and the lowest identified risk among the various financial assets. This paper proposes a model that can efficiently suggest a portfolio that is worth investing. First, a cluster analysis model is introduced in order to categorize a huge amount of stock data into several groups based on their associated return rate and the risk. Several validity indexes are used to select the optimal number of clusters/stocks to be included in the portfolio. Finally, the multi-objective genetic algorithm is used to build portfolio optimization with highest return rate and lowest risk. The proposed model is tested on the data obtained from the Stock Exchange of Thailand.