Search

A large language model (LLM) is constructed to address the sophisticated demands of data retrieval and analysis, detailed well profiling, computation of key technical indicators, and the solutions to complex problems in reservoir performance analysis (RPA). The LLM is constructed for RPA scenarios with incremental pre-training, fine-tuning, and functional subsystems coupling. Functional subsystem and efficient coupling methods are proposed based on named entity recognition (NER), tool invocation, and Text-to-SQL construction, all aimed at resolving pivotal challenges in developing the specific application of LLMs for RDA. This study conducted a detailed accuracy test on feature extraction models, tool classification models, data retrieval models and analysis recommendation models. The results indicate that these models have demonstrated good performance in various key aspects of reservoir dynamic analysis. The research takes some injection and production well groups in the PK3 Block of the Daqing Oilfield as an example for testing. Testing results show that our model has significant potential and practical value in assisting reservoir engineers with RDA. The research results provide a powerful support to the application of LLM in reservoir performance analysis. [ABSTRACT FROM AUTHOR]

Over the past decade, information for precision disease medicine has accumulated in the form of textual data. To effectively utilize this expanding medical text, we proposed a multi-task learning-based framework based on hard parameter sharing for knowledge graph construction (MKG), and then used it to automatically extract gastric cancer (GC)-related biomedical knowledge from the literature and identify GC drug candidates. In MKG, we designed three separate modules, MT-BGIPN, MT-SGTF and MT-ScBERT, for entity recognition, entity normalization, and relation classification, respectively. To address the challenges posed by the long and irregular naming of medical entities, the MT-BGIPN utilized bidirectional gated recurrent unit and interactive pointer network techniques, significantly improving entity recognition accuracy to an average F1 value of 84.5% across datasets. In MT-SGTF, we employed the term frequency-inverse document frequency and the gated attention unit. These combine both semantic and characteristic features of entities, resulting in an average Hits@ 1 score of 94.5% across five datasets. The MT-ScBERT integrated cross-text, entity, and context features, yielding an average F1 value of 86.9% across 11 relation classification datasets. Based on the MKG, we then developed a specific knowledge graph for GC (MKG-GC), which encompasses a total of 9129 entities and 88,482 triplets. Lastly, the MKG-GC was used to predict potential GC drugs using a pre-trained language model called BioKGE-BERT and a drug-disease discriminant model based on CNN-BiLSTM. Remarkably, nine out of the top ten predicted drugs have been previously reported as effective for gastric cancer treatment. Finally, an online platform was created for exploration and visualization of MKG-GC at https://www.yanglab-mi.org.cn/MKG-GC/.

Annotating entities and relationships have been found with the high cost in the joint extraction tasks of entity relationship. There is the strong correlation with the professional fields. It is crucial to improve the extraction performance of the model in the scenarios of low resource. In this study, the reinforcement learning-based joint extraction model was proposed for the entity relationship. Two modules were consisted of: entity recognition and relationship extraction. The extraction efficiency and generalization were improved to jointly extract the entities and relationships in the low resource scenarios. The feature extractor was used to convert the text into feature representations with the richer semantics, which were shared by entity recognition and relationship extraction modules. Entity recognition was realized to utilize the CRF for sequence labeling. The output entity labeling sequence was traversed to locate the entity boundaries, and then connect the entity features for the entity embedding vectors. The limited labeled and abundant unlabeled data was considered in the low resource scenarios. Reinforcement learning was used to train the relationship extraction module. The input of the relationship extraction module included [sentence features, entity embeddings, and relationships] for the labeled data, and [sentence features, and entity embeddings] for the unlabeled data. The improved model was trained to simulate the pseudo labels that generated by unlabeled data in the gradient direction of labeled data, in order to maximize the similarity of the average gradients between them. There was the increase in the diversity and richness of the data, particularly for the better generalization with the less risk of overfitting. Meanwhile, the generated pseudo labels were reduced the dependence on a large amount of labeled data and lower annotation costs. More importantly, the gradient simulation was also balanced the sample distribution of different relationship categories in the dataset, especially in the cases of imbalanced relationship categories. The effectiveness of the model was verified to compare the mainstream models of low resource relationship extraction in the apple cultivation corpus (ATC). The results showed that the F1 score of the model was 88.71%, when the proportion of labeled data reached 30%, indicating the significantly improved model than the rest baselines. In addition, the entity relationships model was effectively extracted from the public dataset TACRED in the low resource scenarios. The proportion of unlabeled data was changed in the ATC and TACRED datasets. The experiments showed that the F1 performance varied on the fixed 10% labeled data and 10%, 30%, 50%, 70%, and 90% unlabeled data. The improved performance was achieved to add the unlabeled data for training. The optimal F1 performance was consistently achieved in the different proportions of unlabeled data. The effectiveness of the gradient simulation module was verified through ablation experiments. The relationship extraction model without gradient simulation module was basically the same as the Self-TrainedBERT model. There was an average F1 decrease of 6.12% in the Self-TrainedBERT model using different proportions of labeled data. The improved performance of the relationship extraction module was attributed to the gradient simulation module, which was improved the quality of pseudo labels. Finally, principal component analysis was used to demonstrate the gradient descent direction of the relationship extraction module for the labeled and pseudo labeled data, representing the quality of pseudo labeled data. The gradient simulation module was also added to gradually approach the ideal local minimum, although the optimization direction of pseudo label data initially fluctuated greatly. The effectiveness of the gradient simulation module was further proved to generate the high-quality pseudo labels. Therefore, the proposed model can effectively extract the entity relationships in the low resource scenarios, indicating the high generalization and performance. [ABSTRACT FROM AUTHOR]

Utilizing deep learning for data mining in biomedicine often falls short in leveraging prior knowledge and adapting to the complexities of biomedical literature mining. Entity recognition, a fundamental task in information extraction, also provides data support for Natural Language Processing (NLP) downstream tasks. Bovine Viral Diarrhea Virus (BVDV) results in considerable economic losses in the cattle industry due to calf diarrhea, bovine respiratory syndrome, and cow abortion. This study aims to extract information on BVDV from relevant literature and build a knowledge base. It enhances feature extraction in the BioBERT pre-trained model using the Machine Reading Comprehension (MRC) framework for information fusion and bi-directionally extracts corpus information through the Bi-LSTM network, followed by a CRF layer for decoding and prediction. The results show the construction of a BVDV Corpus with 22 biomedical entities and introduce the BioBERT-Bi-LSTM-CRF Integrated with MRC (BBCM) model for Named Entity Recognition (NER), combining prior knowledge and the reading comprehension framework (MRC). The BBCM model achieves F 1 -scores of 78.79% and 76.3% on the public datasets JNLPBA and GENIA, respectively, and 67.52% on the BVDV Corpus, outperforming other models. This research presents a targeted NER method for BVDV, effectively identifying related entities and exploring their relationships, thus providing valuable data support for NLP's downstream tasks. [ABSTRACT FROM AUTHOR]

Entity recognition plays a crucial role in various domains, such as natural language processing, information retrieval, and question-answering systems. While significant progress has been made in recognizing entities from plain text, the exploration of entity recognition from multimodal data remains limited due to disparities in semantic representation. In light of this challenge, given the supportive nature of visual and text data, we propose a novel entity recognition model called Heterogeneous Graph Reasoning(HGR), leveraging the synergistic nature of visual and textual data. HGR utilizes image objects to facilitate text entity extraction by mining the potential pair projection between text entity and image object. This is achieved through the utilization of the Vision Refine and Graph Cross Inference modules. In the Vision Refine module, semantically relevant objects hidden in the image are selected to aid in the text entity extraction. In the Graph Cross Inference module, cross-association inference between visual regions and textual entities is constructed through graph construction, heterogeneous graph fusion, visual region refinement and cross inference. To validate the effectiveness of our model, extensive experiments on four multimodal datasets are conducted. Among these datasets, two originate from Chinese unmanned surface vehicles and journalism(USV and NEWS), while the remaining two are public English multimodal datasets(Twitter-2015 and Twitter-2017). The experimental results demonstrate the superiority of our model, with F1-sore improvements of 1.55%, 0.12%, 0.22%, and 0.99% on the four datasets, respectively, when compared to the second-best state-of-the-art model. [ABSTRACT FROM AUTHOR]

In view of the problem that the public data in the field of mine hoist fault is less and the fault knowledge is difficult to be effectively utilized, this paper proposes a method for constructing a mine hoist fault knowledge graph. This method firstly introduces a fault text classification process to deal with the information redundancy problem existing in the target corpus. Then it uses dictionary embedding BERT and BiLSTM-CRF combination for entity recognition, uses ERNIE for entity relation extraction, and stores the extracted triples in Neo4j graph database. On this basis, an intelligent question answering system based on mine hoist fault knowledge graph is realized. This knowledge graph can reveal the complex correlation between mine hoist faults, realize the root cause analysis of related faults, and provide support for mine hoist fault diagnosis. [ABSTRACT FROM AUTHOR]

Using knowledge graph technology for data management can achieve effective representation of fully mechanized coal mining equipment. The information with deep mining value can be obtained. The imbalanced data of fully mechanized coal mining equipment and the limited number of entities in certain categories of equipment affect the precision of entity recognition models. In order to solve the above problems, a knowledge graph construction method for fully mechanized coal mining equipment based on joint coding is proposed. Firstly, the fully mechanized coal mining equipment ontology model is constructed, determining the concepts and relationships. Secondly, the entity recognition model is designed. The model uses Token Embedding, Position Embedding, Sentence Embedding, and Task Embedding 4-layer Embedding structures and Transformer Encoder to encode fully mechanized coal mining equipment data, extract dependency relationships and contextual information features between words. The model introduces a Chinese character library, using the Word2vec model for encoding, extracting semantic rules between characters, and solving the problem of rare characters in fully mechanized coal mining equipment data. The model uses the GRU model to jointly encode the data of fully mechanized coal mining equipment and the character vectors encoded in the font library, and fuse vector features. The model uses the Lattice-LSTM model for character decoding to obtain entity recognition results. Finally, the model uses graph database technology to store and organize extracted knowledge in the form of graphs, completing the construction of knowledge graphs. Experimental verification is conducted on the dataset of fully mechanized coal mining equipment. The results show that the method improves the recognition accuracy of fully mechanized coal mining equipment entities by more than 1.26% compared to existing methods, which to some extent alleviates the low accuracy problem caused by insufficient data when constructing a knowledge graph of fully mechanized coal mining equipment in a small sample situation.

In the process of constructing a knowledge graph for research and develop (R&D) projects, entity extraction for R&D project abstracts helps to quickly understand project content and promote the application and transformation of research results. This article adopts a scientific entity recognition model based on BERT-IDCNN-CRF (BERT combined with Iterative Dilated Convolutional Neural Network and Conditional Random Field) for the entity extraction task in the construction of knowledge graph for R&D projects. This model uses BERT to extract semantic representations from abstract texts, and then uses IDCNN to deeply capture local and global features in the text. Combined with CRF to learn the context transfer relationship between text labels. Finally it achieved the precision of 69.3%, the recall of 65.8%, and the F1-score of 67.5% in scientific entity recognition. On the basis of this model, this article proposes a knowledge graph construction scheme for R&D projects, and constructs a knowledge graph centered on R&D projects, which includes 12 kinds of entities and 13 kinds of relationships. [ABSTRACT FROM AUTHOR]

In the rapidly evolving domain of conversational agents, the integration of Large Language Models (LLMs) into Chatbot Development Platforms (CDPs) is a significant innovation. This study compares the efficacy of employing generic and fine-tuned GPT-3.5-turbo models for designing dialog flows, focusing on the intent and entity recognition crucial for dynamic conversational interactions. Two distinct approaches are introduced: a generic GPT-based system (G-GPT) leveraging the pre-trained model with complex prompts for intent and entity detection, and a fine-tuned GPT-based system (FT-GPT) employing customized models for enhanced specificity and efficiency. The evaluation encompassed the systems' ability to accurately classify intents and recognize named entities, contrasting their adaptability, operational efficiency, and customization capabilities. The results revealed that, while the G-GPT system offers ease of deployment and versatility across various contexts, the FT-GPT system demonstrates superior precision, efficiency, and customization, although it requires initial training and dataset preparation. This research highlights the versatility of LLMs in enriching conversational features for talking assistants, from social robots to interactive chatbots. By tailoring these advanced models, the fluidity and responsiveness of conversational agents can be enhanced, making them more adaptable and effective in a variety of settings, from customer service to interactive learning environments. [ABSTRACT FROM AUTHOR]

This paper aims to structure and semantically describe the information within the industrial chain by constructing an Industry Chain Knowledge Graph (ICKG), enabling more efficient and intelligent information management and analysis. In more detail, this paper constructs a multi-domain industrial chain dataset and proposes a method that combines the top-down establishment of a semantic expression framework with the bottom-up establishment of a data layer to build an ICKG. In the data layer, a deep learning algorithm based on BERT-BiLSTM-CRF is used to extract industry chain entities from relevant literature and reports. The results indicate that the model can effectively identify industry chain entities. These entities and relationships populate a Neo4j graph database, creating a large-scale ICKG for visual display and aiding cross-domain applications. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Entity and relation extraction are key tasks in natural language processing (NLP) and knowledge graph construction. However, existing methods often overlook the complex interactions between entities and their relations. To address this problem, we propose GUniER, which uses a GPT enhancement module and deep bidirectional semantics to optimize the extraction of entities and relations while significantly reducing computational cost. Specifically, the GPT module unifies relation labels with sentence representations, while the BiGRU model captures deep bidirectional semantics to improve the model’s ability to handle complex relations and long-distance dependencies. Additionally, we introduce a two-dimensional interaction table to better model entity-relation interactions, and a cross-entropy loss function to address class imbalance. Experimental results on both open domain and domain-specific datasets show that GUniER achieves a notable improvement in accuracy and reduces computational time compared to state-of-the-art models. Specifically, GUniER achieved a 2.1% improvement in F1 score on the CNShipNet dataset and demonstrated reduced training and inference times compared to previous models, showcasing its efficiency. Our code and models are available at https://anonymous.4open.science/r/UniER.

Name Entity Recognition (NER) aims to recognize entities in the engine room domain from unstructured engine room domain text. But in the engine room domain, the entities are diverse and complex, and there is a nesting phenomenon, resulting in a low entity recognition rate. In this paper, a deep learning method incorporating language models is proposed to enhance the entity recognition performance within the engine room. domain. Firstly, the Bidirectional Encoder Representation from Transformers (BERT) language model is employed to train text feature extraction, acquiring a matrix of vector representations at the word level. Secondly, the trained word vectors are fed into the Bidirectional Gated Recurrent Unit (BiGRU) for contextual semantic entity feature extraction. Finally, the global optimal sequence is extracted by combining with the Conditional Random Field (CRF) model to obtain the named entities in the ship cabin semantics. The experimental results show that the proposed algorithm can obtain better F1 values for all three types of entity recognition. Compared with BERT-BiGRU, the overall accuracy of entity identification, recall rate and F1 value are improved by 1.35%, 1.45% and 1.40%, respectively.

Purposes Event extraction is a prerequisite for building high-quality event knowledge graphs. The dependency of event elements exists in the process of clinical event extraction. Existing methods fail to accurately identify event elements and combine them into events, and the amount of available clinical event tagging data is limited. These problems bring great challenges to the event extraction task. Methods In this research, clinical event is extracted and modelled as an entity recognition model, and a Chinese medical event extraction method incorporating multiple features is proposed: BERT-MCRF. In this method, Bidirectional Encoder Representation from Transformers(BERT) is used to construct the embedding and feature extraction parts of the model, multiple word sliding window features in the Conditional Random Fields(CRF) layer are added, then BERT-MCRF is used as a base experiment for semi-supervised experiments, and a high confidence pseudo-labeled data is proposed. The selection algorithm is used as a condition to filter the data, and 300 data of higher quality are obtained and merged with the original data. Finally, 1 700 corpus are constructed and the model is retrained. Findings The overall F1 value of the BERT-MCRF model on the three attribute entities reaches 80.21%, which is 15.11% better than that of the classical Bi-directional Long Short Term Memory-Conditional Random Fields (BiLSTM-CRF) model; with the model retrained by the semi-supervised idea, the final F1 value reaches 81.56%, which is 1.35% higher than the original BERT-MCRF.

There is scope to enhance agricultural measurement and control systems user interactivity, which typically necessitates training for users to perform specific operations successfully. With the continuous development of natural language semantic processing technology, it has become essential to augment the user-friendliness of multifaceted control and query operations in the agricultural measurement and control sector, ultimately leading to reduced operation costs for users. The study aims to focus on command parsing. The proposed AMR-OPO semantic parsing framework is based on the natural language understanding method of Abstract Meaning Representation of Rooted Markup Graphs (AMR). It transforms the user’s natural language inputs into structured ternary (OPO) statements (operation-place-object) and converts the corresponding parameters of the user’s input commands. The framework subsequently sends the transformed commands to the relevant devices via the IoT gateway. To tackle the intricate task of parsing instructions, we developed a BERT-BiLSTM-ATT-CRF-OPO entity recognition model. This model can detect and extract entities from agricultural instructions, and precisely populate them into OPO statements. Our model shows exceptional accuracy in instruction parsing, with precision, recall, and F-value all measuring at 92.13%, 93.12%, and 92.76%, correspondingly. The findings from our experiment reveal outstanding and precise performance of our approach. It is anticipated that our algorithm will enhance the user experience offered by agricultural measurement and control systems, while also making them more user-friendly. [ABSTRACT FROM AUTHOR]

In the field of Chinese-named entity recognition, recent research has sparked new interest by combining lexical features with character-based methods. Although this vocabulary enhancement method provides a new perspective, it faces two main challenges: firstly, using character-by-character matching can easily lead to conflicts during the vocabulary matching process. Although existing solutions attempt to alleviate this problem by obtaining semantic information about words, they still lack sufficient temporal sequential or global information acquisition; secondly, due to the limitations of dictionaries, there may be words in a sentence that do not match the dictionary. In this situation, existing vocabulary enhancement methods cannot effectively play a role. To address these issues, this paper proposes a method based on lexical information and spatial features. This method carefully considers the neighborhood and overlap relationships of characters in vocabulary and establishes global bidirectional semantic and temporal sequential information to effectively address the impact of conflicting vocabulary and character fusion on entity segmentation. Secondly, the attention score matrix extracted by the point-by-point convolutional network captures the local spatial relationship between characters without fused vocabulary information and characters with fused vocabulary information, aiming to compensate for information loss and strengthen spatial connections. The comparison results with the baseline model show that the SISF method proposed in this paper improves the F1 metric by 0.72%, 3.12%, 1.07%, and 0.37% on the Resume, Weibo, Ontonotes 4.0, and MSRA datasets, respectively. [ABSTRACT FROM AUTHOR]

The named entities of agricultural diseases and pests are featured by complex word-formation and universal phenomena of word combination and entity embedding; in particular, in the domain of Chinese agricultural diseases and pests, there exist a lot of problems including various entity naming modes, fuzzy entity boundary, inadequate feature extraction and inconsistent labeling of entity boundary. To address the above problems, this article combined discourse topic and attention mechanism and proposed the Attention-based SoftLexicon with TF-IDF (ASLT) for agricultural diseases and pests entity recognition. By dividing the words sets based on the positions of characters in the words, merging the discourse topic features into the calculation of lexical information, and introducing the attention mechanism, the recognition accuracy of Chinese agricultural diseases and pests entities can be enhanced. In order to improve the interpretability of the model, we designed a flow chart to explain the major principles and steps, and explained the model through visual methods. This article selected 1061 Chinese agricultural news texts and constructed the Corpus of Chinese Named Entities of Diseases and Pests (CCNEDP), in which 7806 agricultural diseases and pests named entities in total were labeled. According to the present experimental results, the proposed ASLT method can effectively recognize the entities in Chinese agricultural texts and achieve favorable recognition on CCNEDP, with the recognition accuracy, the recall rate and the value of F1 of 93.57, 92.79 and 93.18%, respectively. By contrast with the other entity recognition methods, ASLT shows enhanced recognition performance in terms of accuracy and operating efficiency. The implementation of this work is publicly available at https://github.com/azureskymoon/Lexicon-TFIDF-DTopic-master/tree/master. [ABSTRACT FROM AUTHOR]

Mathematical entity recognition is indispensable for machines to accurately explain and depict mathematical content and to enable adequate mathematical operations and reasoning. It expedites automated theorem proving, speeds up the analysis and retrieval of mathematical knowledge from documents, and improves e-learning and educational platforms. It also simplifies translation, scientific research, data analysis, interpretation, and the practical application of mathematical information. Mathematical entity recognition in the Bangla language is novel; to our best knowledge, no other similar works have been done. Here, we identify the mathematical operator, operands as numbers, and popular mathematical terms (complex numbers, real numbers, prime numbers, etc.). In this work, we recognize Bangla Mathematical Entity Recognition (MER) utilizing the ensemble architecture of deep neural networks known as Bidirectional Encoder Representations from Transformers (BERT). We prepare a novel dataset comprising 13,717 observations, each containing a mathematical statement, mathematical entity, and mathematical type. In our recognition process, we consider our proposed architectures using accuracy, precision, recall and f1-score as the performance metrics. The results have shown a satisfactory accuracy percentage of 97.98 with BERT and 99.76% with ensemble BERT.

In this paper, texture mapping technology is utilized to enhance the virtual reality piano teaching situation, and the piano classroom teaching data is integrated through big data statistical analysis methods. A deep neural network based on BERT+BiLSTM+CRF is used to train a named entity recognition model and complete the construction of a knowledge graph for piano subject data. Then, deep learning methods are used to extract the piano subject data and construct a visualized knowledge graph for the piano subject. Analyze the use of the Piano Smart Classroom teaching platform and the development of a blended teaching mode. The design requirements of the piano intelligent teaching platform are planned from two aspects: platform user roles and platform use cases, and the overall design of the piano intelligent teaching platform is carried out. The use of piano teaching video samples is a tool for calculating the teaching language ratio, analyzing the teaching interactions between teachers and students, and comparing the number of interactions between traditional teaching and smart classroom teaching. Analyze the effectiveness of piano-smart classroom teaching in three dimensions: cognition, emotion, and skill. The mean value of the specific content score of piano intelligent classroom teaching is 3.82, which is the single item with the highest mean value, and the piano teaching classroom supported by smart technology can show the piano teaching content more comprehensively.

In the process of China’s modernization, the organic articulation of the digital economy provides key support. This paper explores the articulation network paradigm of both and proposes a method for building cognitive mapping on a complex network. For the digital modernization industry, the vector representation encoding is completed by using the multi-granularity representation of this paper, and an N-gram encoder realizes the industry entity recognition. A basic idea of relationship template annotation is developed for recognizing entities, and the relationship extraction framework includes three parts: representation learning of templates, quality assessment of templates, and relationship classification model based on template quality. The regression results of the three major economic regions, namely, the eastern region, the central region and the western region, show that the level of digital economy development in the region has a more significant positive effect on the structure of manufacturing output value. The largest regression coefficient is 3.3044 for the eastern region, while the central, western and northeastern regions are 1.85567, 2.45457, and -0.13798, respectively. Through the study of cognitive mapping, the study provides an effective paradigm for Chinese-style modernization.

In this paper, we first studied the construction technology of knowledge graphs, used the BERT model for named entity recognition, extracted the Relationship between different entities through semantic analysis, and stored the database based on table structure and graph structure. Then, the knowledge graph technology is utilized to construct the English interactive teaching platform, and modules such as online classroom, operation and maintenance management, and database are designed to clarify the process of English interactive teaching. Finally, a comparative analysis was conducted to study the effects of English interactive teaching on students’ performance, teaching satisfaction, and classroom behavior. The results show that chi-squared=18.276, df=3, p-value=0.000656, p

Copyright of Electric Power is the property of Electric Power Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Relational triple extraction, a fundamental procedure in natural language processing knowledge graph construction, assumes a crucial and irreplaceable role in the domain of academic research related to information extraction. In this paper, we propose a Double-Headed Entities and Relations Prediction (DERP) framework, which divides the entity recognition process into two stages: head entity recognition and tail entity recognition, using the obtained head and tail entities as inputs. By utilizing the corresponding relation and the corresponding entity, the DERP framework further incorporates a triple prediction module to improve the accuracy and completeness of the joint relation triple extraction. We conducted experiments on two English datasets, NYT and WebNLG, and two Chinese datasets, DuIE2.0 and CMeIE-V2, and compared the English dataset experimental results with those derived from ten baseline models. The experimental results demonstrate the effectiveness of our proposed DERP framework for triple extraction. [ABSTRACT FROM AUTHOR]

Objective: Combining population‐based health registries and electronic health records offers the opportunity to create large, phenotypically detailed patient cohorts of high quality. In this study, we used text mining of clinical notes to confirm International Classification of Diseases, 10th Revision (ICD‐10)‐registered epilepsy diagnoses and classify patients according to focal and generalized epilepsy types. Methods: Using the Danish National Patient Registry, we identified patients who between 2006 and 2016 received an ICD‐10 diagnosis of epilepsy. To validate the epilepsy diagnosis and stratify patients into focal and generalized epilepsy types, we constructed dictionaries for text mining‐based extraction of clinical notes. Two physicians manually reviewed the clinical notes for a total of 527 patients and assigned epilepsy diagnoses, which were compared with the text‐mined diagnoses. Results: We identified 23 632 patients with an ICD‐10 diagnosis of epilepsy, of whom 50% were registered with an unspecified epilepsy diagnosis. In total, 11 211 patients were considered likely to have epilepsy by text mining, with an F1 measure ranging from 82% to 90%. Manual review of the electronic health records for 310 patients revealed a false discovery rate of 29%. This rate was decreased to 4% by the text mining algorithm. The weighted average F1 measure for text mining‐assigned epilepsy types was 79% (82% for focal and 76% for generalized epilepsy). Text mining successfully assigned a focal or generalized epilepsy type to 92% of the text mining‐eligible patients registered with unspecified epilepsy. Significance: Text mining of electronic health records can be used to establish a patient cohort with much higher likelihood of having a diagnosis of epilepsy and a focal or generalized epilepsy type compared to the cohort created from ICD‐10 epilepsy codes alone. We believe the concept will be essential for future genome‐wide and phenome‐wide association studies and subsequently the development of precision medicine for epilepsy patients. [ABSTRACT FROM AUTHOR]

Joint entity and relation extraction (RE) construct a framework for unifying entity recognition and relationship extraction, and the approach can exploit the dependencies between the two tasks to improve the performance of the task. However, the existing tasks still have the following two problems. First, when the model extracts entity information, the boundary is blurred. Secondly, there are mostly implicit interactions between modules, that is, the interactive information is hidden inside the model, and the implicit interactions are often insufficient in the degree of interaction and lack of interpretability. To this end, this study proposes a joint entity and relation extraction model (ESEI) based on Efficient Sampling and Explicit Interaction. We innovatively divide negative samples into sentences based on whether they overlap with positive samples, which improves the model's ability to extract entity word boundary information by controlling the sampling ratio. In order to increase the explicit interaction ability between the models, we introduce a heterogeneous graph neural network (GNN) into the model, which will serve as a bridge linking the entity recognition module and the relation extraction module, and enhance the interaction between the modules through information transfer. Our method substantially improves the model's discriminative power on entity extraction tasks and enhances the interaction between relation extraction tasks and entity extraction tasks. Experiments show that the method is effective, we validate our method on four datasets, and for joint entity and relation extraction, our model improves the F1 score on multiple datasets. [ABSTRACT FROM AUTHOR]

In medical question answering systems, entity recognition plays a major role. Entity recognition based on deep learning has received more and more attention. However, in the medical question answering system, due to the lack of annotated training data, deep learning methods cannot well identify discontinuous and nested entities in medical text. Therefore, a large language model-based entity recognition application method is proposed, and it is applied to the medical problem system. Firstly, the dataset related to medical question answering is processed into text that can be analyzed and processed by a large language model. Secondly, the output of the large language model is classified, and different classifications are processed accordingly. Then, the input text is used for intent recognition, and finally the results of entity recognition and intent recognition are sent to the medical knowledge graph for query, and the answer to the medical question and answer is obtained. Experiments are performed on 3 typical datasets and compared with several typical correlation methods. The results show that the method proposed in this paper performs better. [ABSTRACT FROM AUTHOR]

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.

The upsurge of multifarious endeavors across scientific fields propelled Big Data in the scientific domain. Despite the advancements in management systems, researchers find that mathematical knowledge remains one of the most challenging to manage due to the latter's inherent heterogeneity. One novel recourse being explored is variable typing where current works remain preliminary and, thus, provide a wide room for contribution. In this study, a primordial attempt to implement the end-to-end Entity Recognition (ER) and Relation Extraction (RE) approach to variable typing was made using the BERT (Bidirectional Encoder Representations from Transformers) model. A micro-dataset was developed for this process. According to our findings, the ER model and RE model, respectively, have Precision of 0.8142 and 0.4919, Recall of 0.7816 and 0.6030, and F1-Scores of 0.7975 and 0.5418. Despite the limited dataset, the models performed at par with values in the literature. This work also discusses the factors affecting this BERT-based approach, giving rise to suggestions for future implementations.

Safety instrumented systems (SISs) are installed on process plants to protect against undesired events like e.g., gas leakage and overpressure. A SIS has reliability requirements that are determined during design, and conformance to these requirements should be verified during operation. It is therefore important that all SIS failures are recorded and classified according to their impact on the SIS reliability. Failures of SIS equipment classified as dangerous undetected are of particular interest because they are dormant (undetected) and will prevent the execution of the safety function (dangerous). Analysis of the failure mode and detection method is essential when deciding if a failure is dangerous and undetected. Such information is often provided as unstructured text in notifications registered into the maintenance management system. Therefore, the work of classifying failures requires considerable manual effort in reading and analyzing the texts. Approaches within natural language processing, like technical language processing, have the potential to be deployed more actively for this purpose. However, successful adoption relies on groundwork where classification rules are derived from international standards and commonly agreed industry practice. This paper presents a semi-automated process that incorporates classification rules and gives examples that indicate some of the capabilities of technical language processing for failure classification. The paper also elaborates on how the work relates to Industry 4.0 in creating digital representations to monitor the performance of safety instrumented systems. This work has been carried out as part of the APOS project (Automated process for follow-up of safety instrumented systems). The APOS project has developed knowledge and specifications that simplify and automate the design and operation of safety equipment and investigated how the failure classification process can be made more efficient. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Zhengzhou University (Natural Science Edition) is the property of Journal of Zhengzhou University (Natural Science Edition) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

It is highly significant from a research standpoint and a valuable practice to identify diseases, symptoms, drugs, examinations, and other medical entities in medical text data to support knowledge maps, question and answer systems, and other downstream tasks that can provide the public with knowledgeable answers. However, when contrasted with other languages like English, Chinese words lack a distinct dividing line, and medical entities have problems such as long length and multiple entity types nesting. Therefore, to address these issues, this study suggests a medical named entity recognition (NER) approach that combines part-of-speech and stroke features. First, the text is fed into the BERT pre-training model to get the semantic representation of the text, while the part-of-speech feature vector is obtained using the part-of-speech dictionary, and the stroke feature of the text is extracted through a convolution neural network (CNN). The word vector is then joined with the part-of-speech and stroke feature vectors, respectively, and input into the BiLSTM and CRF layer for training. Additionally, to balance the disparity in data volume across several types of entities, the class-weighted loss function is included in the loss function. According to the experimental findings, our model's F1 score on the CCKS2019 dataset reaches 78.65%, and the recognition performance exceeds many existing algorithms. [ABSTRACT FROM AUTHOR]

With the development of the air traffic management system (ATM), the cyber threat for ATM is becoming more and more serious. The recognition of ATM cyber threat entities is an important task, which can help ATM security experts quickly and accurately recognize threat entities, providing data support for the later construction of knowledge graphs, and ensuring the security and stability of ATM. The entity recognition methods are mainly based on traditional machine learning in a period of time; however, the methods have problems such as low recall and low accuracy. Moreover, in recent years, the rise of deep learning technology has provided new ideas and methods for ATM cyber threat entity recognition. Alternatively, in the convolutional neural network (CNN), the convolution operation can efficiently extract the local features, while it is difficult to capture the global representation information. In Transformer, the attention mechanism can capture feature dependencies over long distances, while it usually ignores the details of local features. To solve these problems, a TextCNN-Flat-Lattice Transformer (TCFLTformer) with CNN-Transformer hybrid architecture is proposed for ATM cyber threat entity recognition, in which a relative positional embedding (RPE) is designed to encode position text content information, and a multibranch prediction head (MBPH) is utilized to enhance deep feature learning. TCFLTformer first uses CNN to carry out convolution and pooling operations on the text to extract local features and then uses a Flat-Lattice Transformer to learn temporal and relative positional characteristics of the text to obtain the final annotation results. Experimental results show that this method has achieved better results in the task of ATM cyber threat entity recognition, and it has high practical value and theoretical contribution. Besides, the proposed method expands the research field of ATM cyber threat entity recognition, and the research results can also provide references for other text classification and sequence annotation tasks. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this paper, a civil aviation travel question and answer (Q&A) method based on integrating knowledge graphs and deep learning technology is proposed to establish a highly efficient travel information Q&A platform and quickly and accurately obtain question information and give corresponding answers to passengers. In the proposed method, a rule-based approach is employed to extract triads from the acquired civil aviation travel dataset to construct a civil aviation travel knowledge graph. Then, the ELECTRA-BiLSTM-CRF model is constructed to recognize the entity, and an improved ALBERT-TextCNN model is used for intent classification. Finally, Cypher query templates are transformed into Cypher query statements and retrieved in the Neo4j database, and the query returns the result, which realizes a new civil aviation travel Q&A method. A self-built civil aviation dataset is selected to prove the effectiveness of the proposed method. The experimental results show that the proposed method based on integrating knowledge graphs and deep learning technology can achieve better Q&A results, and it has better generalization and high accuracy. [ABSTRACT FROM AUTHOR]

It is significant for agricultural intelligent knowledge services using knowledge graph technology to integrate multi-source heterogeneous crop and pest data and fully mine the knowledge hidden in the text. However, only some labeled data for agricultural knowledge graph domain training are available. Furthermore, labeling is costly due to the need for more data openness and standardization. This paper proposes a novel model using knowledge distillation for a weakly supervised entity recognition in ontology construction. Knowledge distillation between the target and source data domain is performed, where Bi-LSTM and CRF models are constructed for entity recognition. The experimental result is shown that we only need to label less than one-tenth of the data for model training. Furthermore, the agricultural domain ontology is constructed by BILSTM-CRF named entity recognition model and relationship extraction model. Moreover, there are a total of 13,983 entities and 26,498 relationships built in the neo4j graph database. [ABSTRACT FROM AUTHOR]

Extracting entity, relation, and attribute information from unstructured text is crucial for constructing large-scale knowledge graphs (KG). Existing research approaches either focus on entity recognition before relation extraction or employ unified annotation. However, these methods overlook the intrinsic relation between entity recognition and relation extraction, resulting in ineffective handling of triple overlap issues where multiple relations share the same entity in a sentence. To address these challenges, this paper proposes an entity-relation joint extraction model comprising two independent sub-modules: one for extracting the head entity and the other for extracting the tail entity and its corresponding relation. The model generates candidate entities and relations by enumerating token sequences in sentences, and then uses the two sub-modules to predict entities and relations. The predicted entities and relations are jointly decoded to obtain relational triples, avoiding error propagation and solving redundancy, entity overlap, and poor generalization. Extensive experiments demonstrate that our model achieves state-of-the-art performance on WebNLG, NYT, WebNLG*, and NYT* public benchmarks. It outperforms all baselines on the WebNLG* dataset, showing significant improvements in different types of triples: normal, SEO, and EPO by 3.8%, 2.9%, and 5.5%, respectively, compared to ETL-Span. For the NYT* dataset, our method improves by 5.7% in triples of Normal type, thereby confirming its effectiveness.