Existing implicit sentiment learning methods mainly focus on capturing implicit sentiment knowledge individually, without paying more attention to the potential connection between implicit and explicit sentiment. From a linguistic perspective, implicit and explicit sentiment expressions are essentially similar when conveying the same sentiment polarity for a specific aspect. In this paper, we present an expression paraphrase strategy and a novel sentiment-consistent contrastive learning mechanism to learn the intrinsic connections between implicit and explicit sentiment expressions and integrate them into the model to enhance implicit sentiment learning. We perform extensive experiments on public datasets, and the results show the significant efficacy of our method on implicit sentiment analysis.

Most of the existing aspect-based sentiment analysis (ABSA) models only predict the sentiment polarity of a single aspect at a time, focusing primarily on enhancing the representation of this single aspect based on the other contexts or aspects. This one-to-one paradigm ignores the fact that multi-aspect, multi-sentiment sentences contain not only distinct specific descriptions for distinct specific aspects, but also shared global context information for multiple aspects. To fully consider these issues, we propose a one-to-many ABSA framework, called You Only Read Once (YORO), that can simultaneously model representations of all aspects based on their specific descriptions and better fuse their relationships using globally shared contextual information in the sentence. Predicting the sentiment polarity of multiple aspects simultaneously is beneficial to improving the efficacy of calculation and prediction. Extensive experiments are conducted on three public datasets (MAMS, Rest14, and Lap14). Experimental results demonstrate the effectiveness of YORO in handling multi-aspect, multi-sentiment scenarios and highlight the promise of one-to-many ABSA in balancing efficiency and accuracy.

Software vulnerability detection aims to identify latent weaknesses in source code to protect software systems from attacks. Most of the current neural network-based approaches rely on preprocessing source codes using code parsers to obtain program dependency graphs for downstream vulnerability detection tasks. However, as source codes may contain incorrect format and special functions, this paradigm may cause parsing errors due to their failure to satisfy the parser's presets or requirements. In addition, modern software development often involves the integration of multiple programming languages, presenting challenges for conventional code parsers that are designed for specific programming languages. To address these issues, we present a novel detection framework that can identify software vulnerabilities in a programming language-agnostic manner without relying on code parsers. We conduct extensive experiments on the CodeXGlue,Reveal, and FUNDED public datasets and evaluate them against leading vulnerability detection benchmarks. Experimental results show that BABEL sets new performance standards, demonstrating superior accuracy and F1 scores across various tasks, including those in language-independent settings, demonstrating the applicability of BABEL in real-world application scenarios. Our code is available at https://github.com/gdufsnlp/BABEL

This work focuses on a novel agricultural application of monitoring and managing summer shoots on citrus fruit trees. To enhance the management efficiency and reliability, a novel scheme based on aerial image analysis was presented to implement intelligent supervision. To this end, we proposed an end-to-end network containing three main modules, i.e. semantic circle detection, circle-inner segmentation, and decision classification. They are respectively in charge of detecting multiple trees, evaluating each tree’s shoot quantity, and predicting management decision for each tree in aerial images. Detailed experiment analysis validates the proposed scheme and network on the aerial images collected from practical citrus orchards.

In agricultural pest management based on computer vision, numerous species of tiny pests need to be detected in images. However, such tiny detection objects are usually missed when adopting deep detection networks. To improve the detection of tiny pests, this paper presented an adaptive tiny object detection network based on the CenterNet framework. Firstly, a branch with a learnable gating function is integrated into the backbone, and supervised learning is performed on it so that tiny pests’ high-resolution feature maps with category and location semantics are exploited, and the learned gating function adaptively controls the combination of such feature maps and the backbone. Moreover, we proposed a size-adaptive weighting method to improve the CenterNet’s detection loss function. In training, a higher weight will be assigned to an instance if its size is smaller or its prediction center is farther from the ground truth. Extensive experiments on multiple datasets verify that our two contributions, i.e. the adaptive-gating branch, and the size-adaptive weighting method, are both help to enhance tiny pests’ weak feature responses and their discriminations, and further improve the IoU accuracies in detection.

MOTIVATION: Targeted therapy for cancer-related genetic variants is critical for precision medicine. Although several databases including The Clinical Interpretation of Variants in Cancer (CIViC), The Oncology Knowledge Base (OncoKB), The Cancer Genome Interpreter (CGI) and My Cancer Genome (MCG) provide clinical interpretations of variants in cancer, the clinical evidence was limited and miscellaneous. In this study, we developed the DrugCVar database, which integrated our manually curated cancer variant-drug targeting evidence from literature and the interpretations from the public resources. RESULTS: In total, 7830 clinical evidences for cancer variant-drug targeting were integrated and classified into 10 evidence tiers. Searching and browsing functions were provided for quick queries of cancer variant-drug targeting evidence. Also, batch annotation module was developed for user-provided massive genetic variants in various formats. Details, such as the mutation function, location of the variants in gene and protein structures and mutation statistics of queried genes in various tumor types, were also provided for further investigations. Thus, DrugCVar could serve as a comprehensive annotation tool to interpret potential drugs for cancer variants especially the massive ones from clinical cancer genomics studies. AVAILABILITY AND IMPLEMENTATION: The database is available at http://drugcvar.omicsbio.info. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.