A Multichannel Model for Microbial Key Event Extraction Based on Feature Fusion and Attention Mechanism

In order to further mine the deep semantic information of the microbial text of public health emergencies, this paper proposes a multichannel microbial sentiment analysis model MCMF-A. Firstly, we use word2vec and fastText to generate word vectors in the feature vector embedding layer and fuse them with lexical and location feature vectors; secondly, we build a multichannel layer based on CNN and BiLSTM to extract local and global features of the microbial text; then we build an attention mechanism layer to extract the important semantic features of the microbial text; thirdly, we merge the multichannel output in the fusion layer and use soft; finally, the results are merged in the fusion layer, and a surtax function is used in the output layer for sentiment classification. The results show that the F1 value of the MCMF-A sentiment analysis model reaches 90.21%, which is 9.71% and 9.14% higher than the benchmark CNN and BiLSTM models, respectively. The constructed dataset is small in size, and the multimodal information such as images and speech has not been considered.

Few-Shot Relation Extraction on Ancient Chinese Documents

Traditional humanity scholars’ inefficient method of utilizing numerous unstructured data has hampered studies on ancient Chinese writings for several years. In this work, we aim to develop a relation extractor for ancient Chinese documents to automatically extract the relations by using unstructured data. To achieve this goal, we proposed a tiny ancient Chinese document relation classification (TinyACD-RC) dataset annotated by historians and contains 32 types of general relations in ShihChi (a famous Chinese history book). We also explored several methods and proposed a novel model that works well on sufficient and insufficient data scenarios, the proposed sentence encoder can simultaneously capture local and global features for a certain period. The paired attention network enhances and extracts relations between support and query instances. Experimental results show that our model achieved promising performance with scarce corpus. We also examined our model on the FewRel dataset and found that outperformed the state-of-the-art no pretraining-based models by 2.27%.

Multichannel Speech Enhancement in Vehicle Environment Based on Interchannel Attention Mechanism

Speech enhancement in a vehicle environment remains a challenging task for the complex noise. The paper presents a feature extraction method that we use interchannel attention mechanism frame by frame for learning spatial features directly from the multichannel speech waveforms. The spatial features of the individual signals learned through the proposed method are provided as an input so that the two-stage BiLSTM network is trained to perform adaptive spatial filtering as time-domain filters spanning signal channels. The two-stage BiLSTM network is capable of local and global features extracting and reaches competitive results. Using scenarios and data based on car cockpit simulations, in contrast to other methods that extract the feature from multichannel data, the results show the proposed method has a significant performance in terms of all SDR, SI-SNR, PESQ, and STOI.

Fine reconstruction of underwater images for environmental feature fusion

Complicated underwater environments, such as occlusion by foreign objects and dim light, causes serious loss of underwater targets feature. Furthermore, underwater ripples cause target deformation, which greatly increases the difficulty of feature extraction. Then, existing image reconstruction models cannot effectively achieve target reconstruction due to insufficient underwater target features, and there is a blurred texture in the reconstructed area. To solve the above problems, a fine reconstruction of underwater images with the target feature missing from the environment feature was proposed. Firstly, the salient features of underwater images are obtained in terms of positive and negative sample learning. Secondly, a layered environmental attention mechanism is proposed to retrieve the relevant local and global features in the context. Finally, a coarse-to-fine image reconstruction model, with gradient penalty constraints, is constructed to obtain the fine restoration results. Contrast experiment between the proposed algorithm and the existing image reconstruction methods has been done in stereo quantitative underwater image data set, real-world underwater image enhancement data set, and underwater image data set, clearly proving that the proposed one is more effective and superior.

The Integration of Linguistic and Geospatial Features Using Global Context Embedding for Automated Text Geocoding

Geocoding is an essential procedure in geographical information retrieval to associate place names with coordinates. Due to the inherent ambiguity of place names in natural language and the scarcity of place names in textual data, it is widely recognized that geocoding is challenging. Recent advances in deep learning have promoted the use of the neural network to improve the performance of geocoding. However, most of the existing approaches consider only the local context, e.g., neighboring words in a sentence, as opposed to the global context, e.g., the topic of the document. Lack of global information may have a severe impact on the robustness of the model. To fill the research gap, this paper proposes a novel global context embedding approach to generate linguistic and geospatial features through topic embedding and location embedding, respectively. A deep neural network called LGGeoCoder, which integrates local and global features, is developed to solve the geocoding as a classification problem. The experiments on a Wikipedia place name dataset demonstrate that LGGeoCoder achieves competitive performance compared with state-of-the-art models. Furthermore, the effect of introducing global linguistic and geospatial features in geocoding to alleviate the ambiguity and scarcity problem is discussed.

MCN-CPI: Multiscale Convolutional Network for Compound–Protein Interaction Prediction

In the process of drug discovery, identifying the interaction between the protein and the novel compound plays an important role. With the development of technology, deep learning methods have shown excellent performance in various situations. However, the compound–protein interaction is complicated and the features extracted by most deep models are not comprehensive, which limits the performance to a certain extent. In this paper, we proposed a multiscale convolutional network that extracted the local and global features of the protein and the topological feature of the compound using different types of convolutional networks. The results showed that our model obtained the best performance compared with the existing deep learning methods.

A Sequence-based Antibody Paratope Prediction Model Through Combing Local-Global Information and Partner Features

Antibodies are proteins which play a vital role in the immune system by recognizing and neutralizing antigens. The region on the antibody binds to the antigens, also known as paratope, mediates antibody-antigen interaction with high affinity and specificity. And the accurate prediction of those regions from antibody sequence contributes to the design of therapeutic antibodies and remains challenging. However, the experimental methods are time-consuming and expensive. In this article, we propose a sequence-based method for antibody paratope prediction by combing the local and global features of antibody sequence and global features of partner antigen sequence. For extracting local features, we use Convolution Neural Networks(CNNs) and a sliding window approach on antibody sequence. For extracting global features, we use Attention-based Bidirectional Long Short-Term Memory(Att-BLSTM) networks on antibody sequence. For extracting partner features, we employ Att-BLSTM on the partner antigen sequence as well. And then, all features are combined to predict antibody paratope by fully-connected networks. The experiments show that our proposed method achieves superior performance over the state-of-the-art sequenced-based antibody paratope prediction methods on benchmark datasets.