Search

In recent years, Community Question Answering (CQA) becomes increasingly prevalent, because it provides platforms for users to collect information and share knowledge. However, given a question in a CQA system, there are often many different paired answers. It is almost impossible for users to view them item by item and select the most relevant one. Hence, answer selection becomes an important task of CQA. In this paper, we propose a novel solution - BertHANK, which is a hierarchical attention networks with enhanced knowledge and pre-trained model for answer selection. Specifically, in the encoding stage, knowledge enhancement and pre-training model are used for questions and answers, respectively. Further, we adopt multi-attention mechanism, including the cross-attention on question-answer pairs, the inner attention on questions at word level, and the hierarchical inner attention on answers at both word and sentence level, to capture more subtle semantic features. In more details, the cross-attention focuses on capturing interactive information among encoded questions and answers. While the hierarchical inner attention assigns different weights to words in sentences, and sentences in answers, thereby obtaining both global and local information of question-answer pairs. The hierarchical inner attention contributes to select out best-matched answers for specific questions. Finally, we integrate attention-questions and attention-answers to make prediction. The results show that our model achieves state-of-the-art performance on two corpora, SemEval-2015 and SemEval-2017 CQA datasets, outperforming the advanced baselines by a large margin. [ABSTRACT FROM AUTHOR]

Gastrointestinal nematodes within the subfamily Ostertagiinae ( Teladorsagia, Ostertagia, and Marshallagia et al.) are among the most common infections of domesticated livestock. These parasites are of particular interest, as many of the species within this group are of economic importance worldwide. Traditionally, nematode species designations have been based on morphological criteria. However, this group possesses poorly defined species. There is an urgent need to develop a reliable technique that can distinguish species of Ostertagiinae. DNA barcoding has been proved to be a powerful tool to identify species of birds, mammals, and arthropods, but this technique has not yet been examined for identifying species of Ostertagiinae. In this study, a total of 138 mitochondrial DNA (mtDNA) cytochrome c oxidase subunit I (COI) sequences from individuals representing 11 species of Ostertagiinae were acquired by PCR for the first time. The specimens were collected from pastoral area of northern China. Genetic divergence analyses showed that mean interspecific Kimura two-parameter distances of COI (13.61 %) were about four times higher than the mean value of the intraspecific divergence (3.69 %). Then, the performance of the COI to identify species of Ostertagiinae was evaluated by identification success rates using nearest neighbor (NN) and BLASTn. The results indicated that the rates of correct sequence identification for COI were high (>80 %) when using the NN and BLASTn methods. Besides, the deep lineage divergences are detected in Teladorsagia circumcincta. Meanwhile, the analyses also detected no genetic differentiation between some species such as Ostertagia hahurica and Ostertagia buriatica. These results indicate that the traditional status of species within Ostertagiinae should be closely examined based on the molecular data. [ABSTRACT FROM AUTHOR]