Though notable progress has been made, neural-based aspect-based sentiment analysis (ABSA) models are prone to learn spurious correlations from annotation biases, resulting in poor robustness on adversarial data transformations. Among the debiasing solutions, causal inference-based methods have attracted much research attention, which can be mainly categorized into causal intervention methods and counterfactual reasoning methods. However, most of the present debiasing methods focus on single-variable causal inference, which is not suitable for ABSA with two input variables (the target aspect and the review). In this paper, we propose a novel framework based on multi-variable causal inference for debiasing ABSA. In this framework, different types of biases are tackled based on different causal intervention methods. For the review branch, the bias is modeled as indirect confounding from context, where backdoor adjustment intervention is employed for debiasing. For the aspect branch, the bias is described as a direct correlation with labels, where counterfactual reasoning is adopted for debiasing. Extensive experiments demonstrate the effectiveness of the proposed method compared to various baselines on the two widely used real-world aspect robustness test set datasets.
A B S T R A C TThe increasing number of small-hold aquaculture ponds globally has raised environmental concerns including the emission of greenhouse gases (GHGs) such as methane (CH 4 ) and nitrous oxide (N 2 O). Aeration is commonly applied to improve oxygen supply for the farmed animals, but it could have opposing effects on GHG emission: It may inhibit anaerobic microbial processes that produce GHGs; it may also increase water-to-air GHG exchange via physical agitation. To resolve the overall effect of aeration on GHG emissions, this study analysed and compared the fluxes of CH 4 and N 2 O between non-aerated and aerated earthen shrimp ponds over two years in a subtropical estuary in southeastern China. CH 4 flux was mainly influenced by water temperature and dissolved oxygen, and it was significantly higher in non-aerated pond (7.6 mg m -2 h -1 ) than in aerated ponds (4.5 mg m -2 h -1 ), with ebullition estimated to account for >90% of the emission. Conversely, non-aerated pond had ca. 50% less N 2 O flux than aerated ponds, with dissolved nitrate as the main environmental driving factor. The combined CO 2 -equivalent sustained global warming potential in aerated ponds (avg. 10829 kg CO 2 -eq ha -1 yr -1 ) was substantially lower than that in non-aerated pond (avg. 17627 kg CO 2 -eq ha -1 yr -1 ). While aeration may increase diffusive flux of GHGs via physical agitation, it remains a simple and effective management practice to decrease the overall climate impact of aquaculture ponds.
The aim of this article was to analyze the clinical and genetic characteristics of a patient with Huntington's disease and her family. We analyzed the clinical data of a patient with Huntington's disease and her family members in the Department of Neurology of our hospital, drew the genetic pedigree, and used gene fragment analysis to detect and analyze the genes of three people in the family according to the principle of informed consent. The genetic pedigree of the family was consistent with that of autosomal dominant diseases. A total of five people in this family developed the disease, two died, and the main clinical manifestations were dystonia, ataxia, and cognitive impairment. Three people in this family underwent genetic testing, and two exhibited normal genotypes. The cytosine-adenine-guanine trinucleotide (CAG) repeats of the proband were abnormally amplified, and the number of repeats reached 43. The main clinical features of the patient included chronic obscure onset, obvious positive family genetic history, clinical features of involuntary limb movement with cognitive impairment, rapid disease progression, poor treatment effect, and abnormal amplification of CAG repeats as shown through genetic testing. All the above features met the diagnostic criteria of Huntington's disease.
Multi-hop fact verification aims to detect the veracity of the given claim by integrating and reasoning over multiple pieces of evidence. Conventional multi-hop fact verification models are prone to rely on spurious correlations from the annotation artifacts, leading to an obvious performance decline on unbiased datasets. Among the various debiasing works, the causal inference-based methods become popular by performing theoretically guaranteed debiasing such as casual intervention or counterfactual reasoning. However, existing causal inference-based debiasing methods, which mainly formulate fact verification as a single-hop reasoning task to tackle shallow bias patterns, cannot deal with the complicated bias patterns hidden in multiple hops of evidence. To address the challenge, we propose Causal Walk, a novel method for debiasing multi-hop fact verification from a causal perspective with front-door adjustment. Specifically, in the structural causal model, the reasoning path between the treatment (the input claim-evidence graph) and the outcome (the veracity label) is introduced as the mediator to block the confounder. With the front-door adjustment, the causal effect between the treatment and the outcome is decomposed into the causal effect between the treatment and the mediator, which is estimated by applying the idea of random walk, and the causal effect between the mediator and the outcome, which is estimated with normalized weighted geometric mean approximation. To investigate the effectiveness of the proposed method, an adversarial multi-hop fact verification dataset and a symmetric multi-hop fact verification dataset are proposed with the help of the large language model. Experimental results show that Causal Walk outperforms some previous debiasing methods on both existing datasets and the newly constructed datasets. Code and data will be released at https://github.com/zcccccz/CausalWalk.
Diagnosis of major depressive disorder (MDD) using resting-state functional connectivity (rs-FC) data faces many challenges, such as the high dimensionality, small samples, and individual difference. To assess the clinical value of rs-FC in MDD and identify the potential rs-FC machine learning (ML) model for the individualized diagnosis of MDD, based on the rs-FC data, a progressive three-step ML analysis was performed, including six different ML algorithms and two dimension reduction methods, to investigate the classification performance of ML model in a multicentral, large sample dataset [1021 MDD patients and 1100 normal controls (NCs)]. Furthermore, the linear least-squares fitted regression model was used to assess the relationships between rs-FC features and the severity of clinical symptoms in MDD patients. Among used ML methods, the rs-FC model constructed by the eXtreme Gradient Boosting (XGBoost) method showed the optimal classification performance for distinguishing MDD patients from NCs at the individual level (accuracy = 0.728, sensitivity = 0.720, specificity = 0.739, area under the curve = 0.831). Meanwhile, identified rs-FCs by the XGBoost model were primarily distributed within and between the default mode network, limbic network, and visual network. More importantly, the 17 item individual Hamilton Depression Scale scores of MDD patients can be accurately predicted using rs-FC features identified by the XGBoost model (adjusted R2 = 0.180, root mean squared error = 0.946). The XGBoost model using rs-FCs showed the optimal classification performance between MDD patients and HCs, with the good generalization and neuroscientifical interpretability.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)