No abstract

No abstract

To effectively prevent river water pollution, water quality monitoring is necessary. However, existing methods for water quality assessment are limited in terms of the characterization of water quality conditions, and few researchers have been able to focus on feature extraction methods relative to water pollution identification, unable to obtain accurate water pollution source information. Thus, this study proposed a feature extraction method based on the entropy-minimal description length principle and gradient boosting decision tree (GBDT) algorithm for identifying the type of surface water pollution in consideration of the distribution characteristics and intrinsic association of conventional water quality indicators. To improve the robustness to noise, we constructed the coarse-grained discretization features of each water quality index based on information entropy. And the nonlinear correlation between water quality indexes and pollution classes was excavated by the GBDT algorithm, which was utilized to acquire tree transformed features. Water samples collected by a southern city Environmental Monitoring Center were used to test the performance of the proposed algorithm. Experimental results demonstrate that features extracted by the proposed method are more effective than the water quality indicators without feature engineering and features extracted by the principal component analysis algorithm.

No abstract

An obstacle to scientific document understanding is the extensive use of acronyms which are shortened forms of long technical phrases. Acronym disambiguation aims to find the correct meaning of an ambiguous acronym in a given text. Recent efforts attempted to incorporate word embeddings and deep learning architectures, and achieved significant effects in this task. In general domains, kinds of fine-grained pretrained language models have sprung up, thanks to the largescale corpora which can usually be obtained through crowdsourcing. However, these models based on domain agnostic knowledge might achieve insufficient performance when directly applied to the scientific domain. Moreover, obtaining large-scale high-quality annotated data and representing high-level semantics in the scientific domain is challenging and expensive. In this paper, we consider both the domain agnostic and specific knowledge, and propose a Hierarchical Dual-path BERT method coined hdBERT to capture the general fine-grained and high-level specific representations for acronym disambiguation. First, the context-based pretrained models, RoBERTa and SciBERT, are elaborately involved in encoding these two kinds of knowledge respectively. Second, multiple layer perceptron is devised to integrate the dualpath representations simultaneously and outputs the prediction. With a widely adopted SciAD dataset contained 62,441 sentences, we investigate the effectiveness of hdBERT. The experimental results exhibit that the proposed approach outperforms state-of-the-art methods among various evaluation metrics. Specifically, its macro F1 achieves 93.73%.