Target Entity Research Articles

MicrobeTCM: A comprehensive platform for the interactions of microbiota and traditional Chinese medicine

Thanks to the advancements in bioinformatics, drugs, and other interventions that modulate microbes to treat diseases have been emerging continuously. In recent years, an increasing number of databases related to traditional Chinese medicine (TCM) or gut microbes have been established. However, a database combining the two has not yet been developed. To accelerate TCM research and address the traditional medicine and micro ecological system connection between short board, we have developed the most comprehensive micro-ecological database of TCM. This initiative includes the standardization of the following advantages: (1) A repeatable process achieved through the standardization of a retrieval strategy to identify literature. This involved identifying 419 experiment articles from PubMed and six authoritative databases; (2) High-quality data integration achieved through double-entry extraction of literature, mitigating uncertainties associated with natural language extraction; (3) Implementation of a similar strategy aiding in the prediction of mechanisms of action. Leveraging drug similarity, target entity similarity, and known drug-target entity association, our platform enables the prediction of the effects of a new herb or acupoint formulas using the existing data. In total, MicrobeTCM includes 171 diseases, 725 microbes, 1468 herb-formulas, 1032 herbs, 15780 chemical compositions, 35 acupoint-formulas, and 77 acupoints. For further exploration, please visit https://www.microbetcm.com.

Nano-modified screen-printed electrode-based electrochemical immunosensors for oral cancer biomarker detection in undiluted human serum and saliva samples.

This proposed work reports the development of in-house made conductive ink-based screen-printed electrodes (SPEs) for label-free detection of oral cancer biomarkers. Carbon ink synthesis includes graphite powder, gum arabic, and water. The selectivity test of the fabricated SPE involves immobilizing antibodies specific to biomarkers and challenges with redox-active interference, other serum molecules, and non-target biomarkers. Three different biomarkers, cytokeratin-19 fragment (CYFRA 21-1), interleukin 8 (IL-8), and tumor protein p53 (TP-53), act as target entities for the detection of oral cancer in patients' samples (serum, N = 28, and saliva, N = 16) at an early stage. The standard technique enzyme-linked immunosorbent assay (ELISA) was employed to estimate the concentration of the biomarkers in serum and saliva samples. SPEs contain amine (-NH2) functional groups involved in covalent bonding with the carboxyl (-COOH) groups of antibody molecules. These immunosensors exhibited remarkably lower detection limits of 829.5 pg mL-1, 0.543 pg mL-1, and 1.165 pg mL-1, and excellent sensitivity of 0.935 μA mL pg-1 cm-1, 0.039 μA mL pg-1 cm-1, and 0.008 μA mL pg-1 cm-1 for CYFRA 21-1, IL-8, and TP-53 biomarkers, respectively. This sensing platform does not require any functionalization for biomolecule immobilization. Thus, it is a cost-effective, disposable, flexible, miniaturized, and sensitive strip to detect oral cancer biomarkers.

Self-Supervised Enhancement for Named Entity Disambiguation via Multimodal Graph Convolution.

Named entity disambiguation (NED) finds the specific meaning of an entity mention in a particular context and links it to a target entity. With the emergence of multimedia, the modalities of content on the Internet have become more diverse, which poses difficulties for traditional NED, and the vast amounts of information make it impossible to manually label every kind of ambiguous data to train a practical NED model. In response to this situation, we present MMGraph, which uses multimodal graph convolution to aggregate visual and contextual language information for accurate entity disambiguation for short texts, and a self-supervised simple triplet network (SimTri) that can learn useful representations in multimodal unlabeled data to enhance the effectiveness of NED models. We evaluated these approaches on a new dataset, MMFi, which contains multimodal supervised data and large amounts of unlabeled data. Our experiments confirm the state-of-the-art performance of MMGraph on two widely used benchmarks and MMFi. SimTri further improves the performance of NED methods. The dataset and code are available at https://github.com/LanceZPF/NNED_MMGraph.

Multistage Competitive Opinion Maximization With Q-Learning-Based Method in Social Networks.

Competitive opinion maximization (COM) aims to determine some individuals (i.e., seed nodes) from social networks, propagating the desired opinions toward a target entity to their neighbors through social relationships when facing with its competitors (components) and maximize the opinion spread after the specific time. Current studies on COM are still in its infancy, while the only work merely considers the scenario that the strategy of competitors is known but ignores the unknown scenario. In addition, previous studies on COM cannot easily address the situation where some users might dynamically change their opinions. To address the COM issue, we investigate the multistage COM and propose a brand-new Q-learning-based opinion maximization framework (QOMF). Our QOMF consists of two components: dynamic opinion propagation and seeding process. We formulate the COM problem by maximizing relative effective opinions. To produce a dynamic opinion series more realistically, we design an opinion propagation model by joining the activation process and a dynamic opinion process. Moreover, we also verify that the opinion propagation model can reach convergence within finite iterations. To acquire the seed nodes, we design a multistage Q-learning seeding scheme by considering known and unknown competitor strategies, respectively. Experimental results on three real datasets demonstrate that the proposed method outperforms the benchmarks on reaching relatively effective opinions.

Hierarchical pattern-based complex query of temporal knowledge graph

The complex query is an essential type of knowledge graph query, which aims to deal with the complex relationships among multiple triples involved in query problems. However, the existing query methods often directly search the target entities in large knowledge graphs, resulting in unsatisfactory query results. In addition, most of the methods focus on static knowledge graphs, ignoring the critical semantic information contained in time elements in query questions. Therefore, this paper proposes a complex query model for temporal knowledge graphs based on the hierarchical pattern. Firstly, aiming at the multi-level semantic relations in complex query problems, we use the entity mapping method to generate the corresponding query graphs. This method can accurately express the semantic relations by learning the constraints, such as time and quantity, in the query problem by manual rules. In addition, to reduce the impact of noisy data on query results, a complex query algorithm based on a hierarchical pattern is proposed. By decomposing the large-scale temporal knowledge graph into smaller knowledge sub-graphs, the search range of target results is effectively reduced. Finally, extensive experiments demonstrate that our model has certain advantages in executing complex queries.

Automatic Context Pattern Generation for Entity Set Expansion

Entity Set Expansion (ESE) is a valuable task that aims to find entities of the target semantic class described by given seed entities. Various Natural Language Processing (NLP) and Information Retrieval (IR) downstream applications have benefited from ESE due to its ability to discover knowledge. Although existing corpus-based ESE methods have achieved great progress, they still rely on corpora with high-quality entity information annotated, because most of them need to obtain the context patterns through the position of the entity in a sentence. Therefore, the quality of the given corpora and their entity annotation has become the bottleneck that limits the performance of such methods. To overcome this dilemma and make the ESE models free from the dependence on entity annotation, our work aims to explore a new ESE paradigm, namely corpus-independent ESE. Specifically, we devise a context pattern generation module that utilizes autoregressive language models (e.g., GPT-2) to automatically generate high-quality context patterns for entities. In addition, we propose the GAPA, a novel ESE framework that leverages the aforementioned <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">G</b> ener <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</b> ted <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PA</b> tterns to expand target entities. Extensive experiments and detailed analyses on three widely used datasets demonstrate the effectiveness of our method. All the codes of our experiments are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/geekjuruo/GAPA</uri> .

TransCP: A Transformer Pointer Network for Generic Entity Description Generation With Explicit Content-Planning

We study neural data-to-text generation to generate a sentence to describe a target entity based on its attributes. Specifically, we address two problems of the encoder-decoder framework for data-to-text generation: i) how to encode a non-linear input (e.g., a set of attributes); and ii) how to order the attributes in the generated description. Existing studies focus on the encoding problem but do not address the ordering problem, i.e., they learn the content-planning implicitly. The other approaches focus on two-stage models but overlook the encoding problem. To address the two problems at once, we propose a model named <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TransCP</b> to explicitly learn content-planning and integrate them into a description generation model in an end-to-end fashion. We propose a novel Transformer-based Pointer Network with <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">gated residual attention</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">importance masking</i> to learn a content-plan. To integrate the content-plan with a description generator, we propose a tracking mechanism to trace the extent to which the content-plan is exposed in the previous decoding time-step. This helps the description generator select the attributes to be mentioned in proper order. Experimental results show that our model consistently outperforms state-of-the-art baselines by up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$2\%$</tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$3\%$</tex-math></inline-formula> in terms of BLEU score on two real-world datasets.

Entity Summarization via Exploiting Description Complementarity and Salience.

Entity summarization is a novel and efficient way to understand real-world facts and solve the increasing information overload problem in large-scale knowledge graphs (KG). Existing studies mainly rely on ranking independent entity descriptions as a list under a certain scoring standard such as importance. However, they often ignore the relatedness and even semantic overlap between individual descriptions. This may seriously interfere with the contribution judgment of descriptions for entity summarization. Actually, the entity summary is a whole to comprehensively integrate the main aspects of entity descriptions, which could be naturally treated as a set. Unfortunately, the exploration of these set characteristics for entity summarization is still an open issue with great challenges. To that end, we draw inspiration from a set completion perspective and propose an entity summarization method with complementarity and salience (ESCS) to deeply exploit description complementarity and salience in order to form a summary set for the target entity. Specifically, we first generate entity description representations with textual features in the description embedding module. For the purpose of learning complementary relationships within the entire summary set, we devise a bi-directional long short-term memory structure to capture global complementarity for each summary in the summary complementarity learning module. Meanwhile, in order to estimate the salience of individual descriptions, we calculate similarities between semantic embeddings of the target entity and its property-value pairs in the description salience learning module. Next, with a joint learning stage, we can optimize ESCS from a set completion perspective. Finally, a summary generation strategy is designed to infer the entire summary set step-by-step for the target entity. Extensive experiments on a public benchmark have clearly demonstrated the effectiveness of ESCS and revealed the potential of set completion in entity summarization task.

Matching method between nanoparticle displacement agent size and pore throat in low permeability reservoir

Nano-particles possess desirable attributes such as small particle size, excellent injectivity, and migration performance, making them highly compatible and adaptable for addressing the water flooding requirements of the low-permeability oil reservoir. When selecting an oil displacement agent for enhancing water flooding and improving oil recovery, factors such as injectivity and migration need to be carefully considered. In this study, through a comprehensive analysis of the mechanism and technical characteristics of nano-particle oil displacement agents, the plugging and profile control mechanisms recognized by the mainstream of nano-particles are elucidated. By examining various elements including outcrop fractures, natural micro-fractures, artificial support fractures, and dynamic monitoring data, a reevaluation of the dominant channel scale governing water drive in low permeability reservoirs is conducted, thereby defining the target entities for profile control and flooding operations. Drawing upon Darcy’s percolation law and leveraging enhanced oil recovery techniques based on the classical Kozeny equation, a profile control and flooding mechanism is proposed that focuses on increasing the specific surface area of polymer particles while simultaneously reducing reservoir permeability. This innovative approach establishes a novel matching method between nano-polymer particles and the diverse media found within the reservoir. Lastly, the application of nanoparticle flooding technology in Changqing Oilfield is presented, highlighting its practical implementation and benefits.

Balanced influence maximization in social networks based on deep reinforcement learning

Balanced influence maximization aims to balance the influence maximization of multiple different entities in social networks and avoid the emergence of filter bubbles and echo chambers. Recently, an increasing number of studies have drawn attention to the study of balanced influence maximization in social networks and achieves success to some extent. However, most of them still have two major shortcomings. First, the previous works mainly focus on spreading the influence of multiple target entities to more users, ignoring the potential influence of the correlation between the target entities and other entities on information propagation in real social networks. Second, the existing methods require a large amount of diffusion sampling for influence estimation, making it difficult to apply to large social networks. To this end, we propose a Balanced Influence Maximization framework based on Deep Reinforcement Learning named BIM-DRL, which consists of two core components: an entity correlation evaluation module and a balanced seed node selection module. Specifically, in the entity correlation evaluation module, an entity correlation evaluation model based on the users’ historical behavior sequences is proposed, which can accurately evaluate the impact of entity correlation on information propagation. In the balanced seed node selection module, a balanced influence maximization model based on deep reinforcement learning is designed to train the parameters in the objective function, and then a set of seed nodes that maximize the balanced influence is found. Extensive experiments on six real-life network datasets demonstrate the superiority of the BIM-DRL over state-of-the-art methods on the metrics of balanced influence spread and balanced propagation accuracy.

BDBRC: A Chinese military entity recognition model combining context contribution and residual dilatation convolutional networks

Military information is gradually overloaded due to the diversity of sources and the exponential growth in quantity, which greatly affects the accuracy of intelligence personnel in extracting and analyzing military information. The modern warfare approach has also evolved from the traditional physical domain to the cognitive domain, and competing for advantages in the cognitive domain has become a key objective of combat. Therefore, constructing domain knowledge graphs and mining the relationships between data play an important role in cognitive domain analysis. In this paper, we propose a convolutional network recognition method based on improved two-layer bi-directional BiLSTM networks named the BERT-α BiLSTMs-RECNN-CRF (BDBRC) model. For the difficulties of military entities generally having long names and low extraction accuracy, as well as the existence of a large number of composite entities that are difficult to recognize, an improved two-layer BiLSTM model is devised first. In view of the fact that the BiLSTMs model always extracts features equally in long-distance text sequences without actually considering the different influences of different sentence contexts, contribution factor a is added to extract the contribution of the above and below to the target entity in different sentences respectively. Then, aiming at the strong problem of the domain of military news texts and the high level of inter-entity ambiguity, we propose a method that utilizes a modified convolutional network (RECNN) for partial feature extraction and jointly with a modified two-layer BiLSTM network for entity recognition. The experiment on the self-constructed dataset shows that the F1 value of the model proposed in this paper reaches 93.18%, and the F1 value, P, and H of our model are all better than the baseline model, which verifies the performance of the model. At the same time, we use public data sets MSRA and CLUB2020, and the experimental results show that the model proposed in this paper also has a good performance in the public data set, verifying the universality of the model. It can provide methodological support for the construction of the military knowledge graph.

Learning entity-oriented representation for biomedical relation extraction

Biomedical Relation Extraction (BioRE) aims to automatically extract semantic relations for given entity pairs and is of great significance in biomedical research. Current popular methods often utilize pretrained language models to extract semantic features from individual input instances, which frequently suffer from overlapping semantics. Overlapping semantics refers to the situation in which a sentence contains multiple entity pairs that share the same context, leading to highly similar information between these entity pairs. In this study, we propose a model for learning Entity-oriented Representation (EoR) that aims to improve the performance of the model by enhancing the discriminability between entity pairs. It contains three modules: sentence representation, entity-oriented representation, and output. The first module learns the global semantic information of the input instance; the second module focuses on extracting the semantic information of the sentence from the target entities; and the third module enhances distinguishability among entity pairs and classifies the relation type. We evaluated our approach on four BioRE tasks with eight datasets, and the experiments showed that our EoR achieved state-of-the-art performance for PPI, DDI, CPI, and DPI tasks. Further analysis demonstrated the benefits of entity-oriented semantic information in handling multiple entity pairs in the BioRE task.

A novel Data and Model Centric artificial intelligence based approach in developing high-performance Named Entity Recognition for Bengali Language.

Named Entity Recognition (NER) plays a significant role in enhancing the performance of all types of domain specific applications in Natural Language Processing (NLP). According to the type of application, the goal of NER is to identify target entities based on the context of other existing entities in a sentence. Numerous architectures have demonstrated good performance for high-resource languages such as English and Chinese NER. However, currently existing NER models for Bengali could not achieve reliable accuracy due to morphological richness of Bengali and limited availability of resources. This work integrates both Data and Model Centric AI concepts to achieve a state-of-the-art performance. A unique dataset was created for this study demonstrating the impact of a good quality dataset on accuracy. We proposed a method for developing a high quality NER dataset for any language. We have used our dataset to evaluate the performance of various Deep Learning models. A hybrid model performed with the exact match F1 score of 87.50%, partial match F1 score of 92.31%, and micro F1 score of 98.32%. Our proposed model reduces the need for feature engineering and utilizes minimal resources.

Extracting Mutant-Affected Protein-Protein Interactions via Gaussian-Enhanced Representation and Contrastive Learning.

Genetic mutations can impact protein-protein interactions (PPIs) in biomedical literature. Automated extraction of PPIs affected by gene mutations from biomedical literature can aid in evaluating the clinical importance of gene variations, which is crucial for the advancement of precision medicine. In this study, a new model called the Gaussian-enhanced representation model (GRM) is introduced for PPI extraction. The model utilizes the Gaussian probability distribution to produce a target entity representation based on the BioBERT pretraining model. The GRM assigns more weight to target protein entities and their adjacent entities, resolving the problem of lengthy input text and scattered distribution of target entities in the PPI extraction task. Additionally, the model introduces a supervised contrast learning approach to enhance its effectiveness and robustness. Experiments on the BioCreative VI data set demonstrate that our proposed GRM model has achieved state-of-the-art performance.

Sinophobia was popular in Chinese language communities on Twitter during the early COVID-19 pandemic

The COVID-19 pandemic has led to a global surge in Sinophobia. We examine how Chinese language users responded to COVID-19 on Western social media by compiling a unique database (CNTweets) with over 25 million Chinese tweets mentioning any Chinese characters related to China, the Chinese Communist Party (CCP), Chinese, and Asians from December 2019 to April 2021. Our analysis of Twitter users’ self-reported geographic information shows that most Chinese language users on Twitter originated from Mainland China, Hong Kong, Taiwan, and the United States. We then adopt the Robustly Optimized Bidirectional Encoder Representations from Transformers (RoBERTa) and structural topic modeling to further analyze the sentiments, content, and topics of Chinese tweets during the COVID-19 pandemic. Our results suggest that 61.8% of tweets in our database were contributed by only 1% of Twitter users and 62.2% of tweets were negative toward China. Despite the prevalence of anti-China sentiments, the target entity analysis shows that these negative sentiments were more likely to target the Chinese government and CCP than the Chinese people. Our findings also show that the most popular topics were politics (e.g., Hong Kong protests and Taiwan issues), COVID-19, and the United States (e.g., the US-China relations and domestic issues). Anti-China users focused relatively more on political issues such as democracy and freedom, while pro-China users mentioned cultural and economic topics more. Our social network analysis reveals that these pro-China and anti-China Twitter users lacked in-depth engagement in China-related conversations and were highly segregated from each other. We conclude by discussing our contributions to China and social media studies and possible policy implications.

Online Reviews System using Aspect Based Sentimental Analysis &amp; Opinion Mining

Aspect extraction is the most critical and thoroughly researched process in SA (Sentiment Analysis) for conducting an accurate classification of feelings. Over the last decade, massive amounts of research have focused on identifying and removing elements. Products have centralized distribution channels, and certain apps may occasionally operate close to the most recent product to be created. Any e-commerce business enterprise must analyses user / customer feedback in order to provide better products and services to them. Because broad reviews frequently include remarks in a consolidated manner when a customer gives his thoughts on various product attributes within the same summary, it is difficult to determine the exact feeling. The key components of this software are included in their release, making it a valuable tool for management to improve the consistency of their own system's specifications. The goal was to categories the aspects of the target entities provided, as well as the feelings conveyed for each aspect. First, we are implementing a supervised classification framework that is tightly restricted and relies solely on training sets for knowledge. As a result, the key terms comes from associated at various elements of a thing within its entirety perform customer sentiment using certain elements. In contrast to current sentiment analysis approaches, synthetic and actual data set experiments yield positive results.

Mining heuristic evidence sentences for more interpretable document-level relation extraction

Current research on evidence sentences is aimed at developing document-level relational extraction models with improved interpretability. Evidence sentences extracted using existing methods are often incomplete, leading to poor relationship prediction accuracy. To address this problem, we developed a novel efficient heuristic rule and entity representation method. First, a heuristic rule is constructed according to the interactions between different mentions of the head and tail entities of the target entity pair, and evidence sentences are subsequently extracted. Second, pseudo documents, constructed according to the original document order, are used as input text to remove noisy statements. Finally, different representations of the same entity in different entity pairs are learned to represent it more accurately through the interactive mention of head and tail entities. Experiments on the document-level general domain dataset DocRED indicated that our heuristic rules improved sentence extraction by 6.01% compared to that achieved by the baseline model Paths-BiLSTM. In terms of relation prediction, the accuracy of the proposed method was comparable to those of existing models that use the entire document as input text; however, the input text used by the proposed method was shorter and more interpretable.

Improving Drug-Drug Interaction Extraction with Gaussian Noise.

Drug-Drug Interactions (DDIs) produce essential and valuable insights for healthcare professionals, since they provide data on the impact of concurrent administration of medications to patients during therapy. In that sense, some relevant works, related to the DDIExtraction2013 Challenge, are available in the current technical literature. This study aims to improve previous results, using two models, where a Gaussian noise layer is added to achieve better DDI relationship extraction. (1) A Piecewise Convolutional Neural Network (PW-CNN) model is used to capture relationships among pharmacological entities described in biomedical databases. Additionally, the model incorporates multichannel words to enrich a person's vocabulary and reduce unfamiliar words. (2) The model uses the pre-trained BERT language model to classify relationships, while also integrating data from the target entities. After identifying the target entities, the model transfers the relevant information through the pre-trained architecture and integrates the encoded data for both entities. The results of the experiment show an improved performance, with respect to previous models.

A practical guide to separate and concentrate ALNs and femtoplankton entities

The development of new technologies of microscopy, flow cytometry and genomics has allowed a profound reconsideration of the diversity and ecological role of femtoplankton entities (i.e., viruses, vesicles, aster like nanoparticles –ALNs–). Among these, the discovery of ALNs, raise serious questions about their exact nature and their biological and environmental roles. The elaboration of a practical guide for the concentration and separation of femtoplankton entities, including ALNs, is necessary for a better understanding of their diversity, ontogeny, and ecology. Here, we propose a step-by-step procedure for the enrichment and isolation of femtoplankton entities and prokaryotes. The established protocol couples tangential flow filtration to differential centrifugation, leading to differentiate enriched samples (with different target entity contents), usable as a matrix for sorting by flow cytometry. All entities were identified, characterized and counted by transmission electron microscopy and flow cytometry.The procedure allows an efficient detection, concentration and separation of femtoplankton entities (up to purity rate of 92, 67, 81 and 85% for virus like particles, vesicles, prokaryotes and ALNs, respectively), and different morphotypes of ALNs into different fractions (up to 51, 72, 52, 40 and 79% of total ALNs for 20-, 11-, budding 11-, 5–10- and 4-armed ALNs, respectively).

Relation extraction: advancements through deep learning and entity-related features.

Capturing semantics and structure surrounding the target entity pair is crucial for relation extraction. The task is challenging due to the limited semantic elements and structural features of the target entity pair within a sentence. To tackle this problem, this paper introduces an approach that fuses entity-related features under convolutional neural networks and graph convolution neural networks. Our approach combines the unit features of the target entity pair to generate corresponding fusion features and applies the deep learning framework to extract high-order abstract features for relation extraction. Experimental results from three public datasets (ACE05 English, ACE05 Chinese, and SanWen) indicate that the proposed approach achieves F1-scores of 77.70%, 90.12%, and 68.84%, respectively, highlighting its effectiveness and robustness. This paper provides a comprehensive description of the approach and experimental results.