Drug-drug interactions (DDIs) are a significant focus in biomedical research and clinical practice due to their potential to compromise treatment outcomes or cause adverse effects. While deep learning approaches have advanced DDI extraction, challenges such as severe class imbalance and the complexity of biomedical relationships persist. This study introduces BioFocal-DDI, a framework combining BioGPT for data augmentation, BioBERT and BiLSTM for contextual and sequential feature extraction, and Relational Graph Convolutional Networks (ReGCN) for relational modeling. To address class imbalance, a Focal Loss-based Attention mechanism is employed to enhance learning on underrepresented and challenging instances. Evaluated on the DDI Extraction 2013 dataset, BioFocal-DDI achieves a precision of 86.75%, recall of 86.53%, and an F1 Score of 86.64%. These results suggest that the proposed method is effective in improving DDI extraction.

For natural language understanding tasks, either machine reading comprehension or natural language inference, both semantics-aware and inference are favorable features of the concerned modeling for better understanding performance. Thus we propose a Semantics-Aware Inferential Network (SAIN) to meet such a motivation. Taking explicit contextualized semantics as a complementary input, the inferential module of SAIN enables a series of reasoning steps over semantic clues through an attention mechanism. By stringing these steps, the inferential network effectively learns to perform iterative reasoning which incorporates both explicit semantics and contextualized representations. In terms of well pre-trained language models as front-end encoder, our model achieves significant improvement on 11 tasks including machine reading comprehension and natural language inference.

As the most popular way of communication technology at the moment, wireless sensor networks have been widely concerned by academia and industry and plays an important role in military, agriculture, medicine, and other fields. Identity authentication offers the first line of defence to ensure the security communication of wireless sensor networks. Since the sensor nodes are resource-limited in the wireless networks, how to design an efficient and secure protocol is extremely significant. The current authentication protocols have the problem that the sensor nodes need to execute heavy calculation and communication consumption during the authentication process and cannot resist node capture attack, and the protocols also cannot provide perfect forward and backward security and cannot resist replay attack. Multifactor identity authentication protocols can provide a higher rank of security than single-factor and two-factor identity authentication protocols. The multigateway wireless sensor networks’ structure can provide a larger communication coverage area than the single-gateway network structure, so it has become the focus of recent studies. Therefore, we design a novel multifactor authentication protocol for multigateway wireless sensor networks, which only apply the lightweight hash function and are given biometric information to achieve a higher level of security and efficiency and a larger communication coverage area. We separately apply BAN logic, random oracle model, and AVISPA tool to validate the security of our authentication protocol in Case 1 and Case 2. We put forward sixteen evaluation criteria to comprehensively evaluate our authentication protocol. Compared with the related authentication protocols, our authentication protocol is able to achieve higher security and efficiency.

The latest work on language representations carefully integrates contextualized features into language model training, which enables a series of success especially in various machine reading comprehension and natural language inference tasks. However, the existing language representation models including ELMo, GPT and BERT only exploit plain context-sensitive features such as character or word embeddings. They rarely consider incorporating structured semantic information which can provide rich semantics for language representation. To promote natural language understanding, we propose to incorporate explicit contextual semantics from pre-trained semantic role labeling, and introduce an improved language representation model, Semantics-aware BERT (SemBERT), which is capable of explicitly absorbing contextual semantics over a BERT backbone. SemBERT keeps the convenient usability of its BERT precursor in a light fine-tuning way without substantial task-specific modifications. Compared with BERT, semantics-aware BERT is as simple in concept but more powerful. It obtains new state-of-the-art or substantially improves results on ten reading comprehension and language inference tasks.

Multi-choice reading comprehension is a challenging task to select an answer from a set of candidate options when given passage and question. Previous approaches usually only calculate question-aware passage representation and ignore passage-aware question representation when modeling the relationship between passage and question, which cannot effectively capture the relationship between passage and question. In this work, we propose dual co-matching network (DCMN) which models the relationship among passage, question and answer options bidirectionally. Besides, inspired by how humans solve multi-choice questions, we integrate two reading strategies into our model: (i) passage sentence selection that finds the most salient supporting sentences to answer the question, (ii) answer option interaction that encodes the comparison information between answer options. DCMN equipped with the two strategies (DCMN+) obtains state-of-the-art results on five multi-choice reading comprehension datasets from different domains: RACE, SemEval-2018 Task 11, ROCStories, COIN, MCTest.