Types Of Entities Research Articles

Building a knowledge graph to enrich ChatGPT responses in manufacturing service discovery

Sourcing and identification of new manufacturing partners is crucial for manufacturing system integrators to enhance agility and reduce risk through supply chain diversification in the global economy. The advent of advanced large language models has captured significant interest, due to their ability to generate comprehensive and articulate responses across a wide range of knowledge domains. However, the system often falls short in accuracy and completeness when responding to domain-specific inquiries, particularly in areas like manufacturing service discovery. This research explores the potential of leveraging Knowledge Graphs in conjunction with ChatGPT to streamline the process for prospective clients in identifying small manufacturing enterprises. In this study, we propose a method that integrates bottom-up ontology with advanced machine learning models to develop a Manufacturing Service Knowledge Graph from an array of structured and unstructured data sources, including the digital footprints of small-scale manufacturers throughout North America. The Knowledge Graph and the learned graph embedding vectors are leveraged to tackle intricate queries within the digital supply chain network, responding with enhanced reliability and greater interpretability. The approach highlighted is scalable to millions of entities that can be distributed to form a global Manufacturing Service Knowledge Network Graph that can potentially interconnect multiple types of Knowledge Graphs that span industry sectors, geopolitical boundaries, and business domains. The dataset developed for this study, now publicly accessible, encompasses more than 13,000 manufacturers’ weblinks, manufacturing services, certifications, and location entity types.

Language model based on deep learning network for biomedical named entity recognition

Biomedical Named Entity Recognition (BioNER) is one of the most basic tasks in biomedical text mining, which aims to automatically identify and classify biomedical entities in text. Recently, deep learning-based methods have been applied to Biomedical Named Entity Recognition and have shown encouraging results. However, many biological entities are polysemous and ambiguous, which is one of the main obstacles to the task of biomedical named entity recognition. Deep learning methods require large amounts of training data, so the lack of data also affect the performance of model recognition. To solve the problem of polysemous words and insufficient data, for the task of biomedical named entity recognition, we propose a multi-task learning framework fused with language model based on the BiLSTM-CRF architecture. Our model uses a language model to design a differential encoding of the context, which could obtain dynamic word vectors to distinguish words in different datasets. Moreover, we use a multi-task learning method to collectively share the dynamic word vector of different types of entities to improve the recognition performance of each type of entity. Experimental results show that our model reduces the false positives caused by polysemous words through differentiated coding, and improves the performance of each subtask by sharing information between different entity data. Compared with other state-of-the art methods, our model achieved superior results in four typical training sets, and achieved the best results in F1 values.

CEPTNER: Contrastive learning Enhanced Prototypical network for Two-stage few-shot Named Entity Recognition

Few-shot Named Entity Recognition (NER) systems aim to classify unseen named entity types with limited labeled examples. Significant progress has been made in the use of large-scale pre-trained language models. However, boundary information and hidden relationships between entities beyond the sequence, which provide additional information and play crucial roles in few-shot NER, have received little attention in recent methods that achieve the state of the art. In this paper, we propose CEPTNER, a Contrastive learning Enhanced Prototypical network for Two-stage few-shot Named Entity Recognition, which leverages meta-learning and prototypical network to identify unseen entity types with limited labeled data. Concretely, we first detect candidate boundaries of entities in the stage of boundary detector, then we employ a prototypical network to filter false boundaries and type for the remaining spans in the stage of entity classifier. Additionally, we conduct entity-level contrastive learning to explore the internal relationship between entities that provides extra information while optimizing the prototypical network. CEPTNER is evaluated on two widely-used few-shot NER datasets and a few-shot slot tagging dataset: Few-NERD, CrossNER and SNIPS. Extensive experiments on various benchmarks show the superiority of CEPTNER over previous methods for few-shot NER.

Incorporating Entity Type-Aware and Word–Word Relation-Aware Attention in Generative Named Entity Recognition

Named entity recognition (NER) is a critical subtask in natural language processing. It is particularly valuable to gain a deeper understanding of entity boundaries and entity types when addressing the NER problem. Most previous sequential labeling models are task-specific, while recent years have witnessed the rise of generative models due to the advantage of tackling NER tasks in the encoder–decoder framework. Despite achieving promising performance, our pilot studies demonstrate that existing generative models are ineffective at detecting entity boundaries and estimating entity types. In this paper, a multiple attention framework is proposed which introduces the attention of entity-type embedding and word–word relation into the named entity recognition task. To improve the accuracy of entity-type mapping, we adopt an external knowledge base to calculate the prior entity-type distributions and then incorporate the information input to the model via the encoder’s self-attention. To enhance the contextual information, we take the entity types as part of the input. Our method obtains the other attention from the hidden states of entity types and utilizes it in self- and cross-attention mechanisms in the decoder. We transform the entity boundary information in the sequence into word–word relations and extract the corresponding embedding into the cross-attention mechanism. Through word–word relation information, the method can learn and understand more entity boundary information, thereby improving its entity recognition accuracy. We performed experiments on extensive NER benchmarks, including four flat and two long entity benchmarks. Our approach significantly improves or performs similarly to the best generative NER models. The experimental results demonstrate that our method can substantially enhance the capabilities of generative NER models.

The issue of legal regulation of administrative procedures on the example of foreign countries

The article deals with the issue of legal regulation of administrative procedures on the example of foreign countries. The standards of the administrative procedure regarding the adoption of administrative decisions, i.e. decisions of public administration bodies, which concern the rights and obligations of individuals and legal entities, are considered. The content and peculiarities of legal regulation of administrative procedures in foreign countries, the scope and subject of legal regulation through the prism of the legislation of foreign countries on administrative procedures are outlined. Various approaches to determining the scope, content and methods of its legal regulation are analyzed.
 Attention is focused on the specifics of managerial activity, which must take effective measures in a timely manner in a wide variety of situations, forming the boundaries and restrictions necessary in the rule of law. The types of entities to which administrative procedures apply have been considered.
 The rights and obligations of administrative bodies regarding the preparation and adoption of an administrative decision are defined. Features of appeals by individuals and legal entities, definition of sub-agency category of cases are outlined. The types of decisions made by the administrative body are classified. Emphasis is placed on informing persons whose interests may be affected by an administrative act.
 The grounds for removing officials considered biased are outlined. The rights of citizens participating in the administrative procedure are considered separately.

BioBBC: a multi-feature model that enhances the detection of biomedical entities

The rapid increase in biomedical publications necessitates efficient systems to automatically handle Biomedical Named Entity Recognition (BioNER) tasks in unstructured text. However, accurately detecting biomedical entities is quite challenging due to the complexity of their names and the frequent use of abbreviations. In this paper, we propose BioBBC, a deep learning (DL) model that utilizes multi-feature embeddings and is constructed based on the BERT-BiLSTM-CRF to address the BioNER task. BioBBC consists of three main layers; an embedding layer, a Long Short-Term Memory (Bi-LSTM) layer, and a Conditional Random Fields (CRF) layer. BioBBC takes sentences from the biomedical domain as input and identifies the biomedical entities mentioned within the text. The embedding layer generates enriched contextual representation vectors of the input by learning the text through four types of embeddings: part-of-speech tags (POS tags) embedding, char-level embedding, BERT embedding, and data-specific embedding. The BiLSTM layer produces additional syntactic and semantic feature representations. Finally, the CRF layer identifies the best possible tag sequence for the input sentence. Our model is well-constructed and well-optimized for detecting different types of biomedical entities. Based on experimental results, our model outperformed state-of-the-art (SOTA) models with significant improvements based on six benchmark BioNER datasets.

Challenges and progress in applying space technology in support of the sustainable development goals

The global community, with coordination from the United Nations, is energized to pursue the Sustainable Development Goals (SDGs), a list of 17 important aspirations that summarize the key challenges of our era. The SDGs apply to every nation and represent an international effort to eliminate extreme poverty, ensure access to safe drinking water, strengthen food security, and produce clean and reliable energy, among other pursuits. Space technology is already being used around the world to advance progress toward the SDGs and monitor their related Indicators. This paper explores how six technologies related to space—satellite Earth observation, satellite communication, satellite navigation and positioning, human spaceflight and microgravity research, space technology transfer, and basic scientific research—are being used to realize the vision that the SDGs represent. The paper also discusses the obstacles that limit the application of these technologies for the SDGs and provides an overview of potential paths to overcome these barriers. The paper finally studies the historical and potential roles that four distinct types of entities involved in global sustainable development—governments, non- and inter-governmental organizations, entrepreneurial companies, and universities— have played or may play in the application of space technologies towards the SDGs.

Indigenous research ethics and Tribal Research Review Boards in the United States: examining online presence and themes across online documentation

Researchers seeking to engage in projects related to Tribal communities and their citizens, lands, and non-human relatives are responsible for understanding and abiding by each Tribal nation’s research laws and review processes. Few studies, however, have described the many diverse forms of Tribal research review systems across the United States (US). This study provides one of the most comprehensive examinations of research review processes administered by Tribal Research Review Boards (TRRBs) in the US. Through a systematic analysis, we consider TRRBs’ online presence, online documentation, and themes across documents, for five entity types: Tribal nations and Tribal consortiums, Tribal colleges and universities, Tribal health organizations, Indian Health Services, and other Tribal organizations. Results include an assessment of online presence for 98 potential TRRBs, identification of 118 publicly available online documents, and analysis of 41 themes across four document types: Tribal research codes and TRRBs’ guidelines, applications, and post-approval documents. Altogether, this research provides a macro-level analysis of the most common types of TRRBs in the US in an effort to increase researchers’ understanding of these important processes as they prepare to ethically engage Tribal communities in research. These results aim to empower Tribal decision makers as they align their TRRBs’ online visibility and documentation with community priorities and strengthen their protections for the rights and wellbeing of their citizens and community. Ultimately, by expanding our knowledge of TRRBs across the US, this contribution seeks to uphold Tribal sovereignty in research and promote ethical approaches to research with Indigenous communities.

COMPLIANCE AND LEGISLATION IN THE FIELD OF INTELLECTUAL PROPERTY

This article is devoted to the study of the institute of compliance, the need to implement compliance procedures in an organization regardless of the form of ownership, type of legal entity, organizational and legal form. This business process has been widely implemented in the financial sector, but due to the spread of the introduction of economic sanctions and threats of secondary sanctions, it has become particularly relevant in Kazakhstan. This article analyzes the issues of the essence of compliance, procedures, goals and objectives, functions of services, types of compliance, negative consequences of non-compliance with legal requirements, corporate norms, ethical standards and internal regulatory documents. In the article, the author substantiates the need to include in the functions of compliance controllers the study of risks in the sphere of intellectual property turnover, which is a necessary measure of compliance with legal norms on intellectual property, not limited only to the introduction of anti-corruption, sanctions or antimonopoly compliance. In practice, these areas are well-established. However, illegal turnover of intellectual property, violations of exclusive rights create serious legal risks and financial consequences. In this regard, the author considers it necessary to implement compliance depending on the type of activity of the company, including for compliance with intellectual property legislation. This position is based on numerous facts of judicial proceedings, criminal and administrative prosecution of offenders who, when applying this type of compliance control, could have prevented violations of intellectual property law in advance. The introduction of compliance control in this area would prevent the onset of legal consequences and financial losses (fines, confiscation).

Substance use disorder treatment carve outs in Medicaid managed care

IntroductionMedicaid managed care organizations (MCO) play a major role in addressing the nation's epidemic of drug overdose and mortality by administering substance use disorder (SUD) treatment benefits for over 50 million Americans. While it is known that some Medicaid MCO plans delegate responsibility for managing SUD treatment benefits to an outside “carve out” entity, the extent and structure of such carve out arrangements are unknown. This is an important gap in knowledge, given that carve outs have been linked to reductions in rates of SUD treatment receipt in several studies. To address this gap, we examined carve out arrangements used by Medicaid MCO plans to administer SUD treatment benefits in ten states. MethodsData for this study was gleaned using a purposive sampling approach through content analysis of publicly available benefits information (e.g., member handbooks, provider manuals, prescription drug formularies) from 70 comprehensive Medicaid MCO plans in 10 selected states (FL, GA, IL, MD, MI, NH, OH, PA, UT, and WV) active in 2018. Each Medicaid MCO plan's documents were reviewed and coded to indicate whether a range of SUD treatment services (e.g., inpatient treatment, outpatient treatment, residential treatment) and medications were carved out, and if so, to what type of entity (e.g., behavioral health organization). ResultsA large majority of Medicaid MCO plans carved out at least some (28.6 %) or all (40.0 %) SUD treatment services, with nearly all plans carving out some (77.1 %) or all (14.3 %) medications, mainly due to the carving out of methadone treatment. Medicaid MCO plans most commonly carved out SUD treatment services to behavioral health organizations, while most medications were carved out to state Medicaid fee-for-service plans. ConclusionsCarve out arrangements for SUD treatment vary dramatically across states, across plans, and even within plans. Given that some studies have linked carve out arrangements to reductions in treatment access, their widespread use among Medicaid MCO plans is cause for further consideration by policymakers and other key interest groups. Moreover, reliance on such complex arrangements for administering care may create challenges for enrollees who seek to learn about and access plan benefits.

Application of Business Judgement Rule Doctrine in Case Settlement (Case Study of Corruption Crime of PT Asuransi Jiwasraya (Persero))

As is known in Corporate Law, corporate law experts divide 2 (two) major groups of business entity forms, one of which is a legal entity. Included in this group is the Limited Liability Company (PT) The thing that distinguishes between the two types of business entities incorporated and unincorporated lies in the responsibility of the company owner. In relation to practice, business people are more interested in establishing a business entity in the form of a legal entity, namely a Limited Liability Company ("PT"). The reasons why business people are more likely to choose a PT, namely the continuity of a business entity in the form of a PT does not depend on the personalities of the owners but on the capital accumulated, the separation of responsibilities between the company owner and the company, and because PT can be used as a means to move towards a more liberal and open business. In carrying out the management of a PT, the Board of Directors performs its duties with reference to the principle of good faith. In this case, it is actually difficult to distinguish which actions are actually carried out in good faith and which actions are reasonable in carrying out their duties. In relation to its duties and authorities, the management of the Company carried out by the Board of Directors includes running business activities, controlling, and making business decisions that have an impact on the Company, even though these decisions can cause profits or losses.

Features of Delimitation of Crimes Provided for in Articles 285 of the Criminal Code and 286 of the Criminal Code when they are Committed in the Public Procurement

The specifics of the criminal law regulation of liability for abuse of official powers and their excess committed in the field of public procurement are determined by the specifics of the regulation of the activities of officials participating in this sphere within the framework of their “procurement” and related functions. The correct qualification of acts committed in the field of public procurement requires reference to numerous regulations of the legislation on the contract system and on the procurement of goods, works, services by certain types of legal entities. The need to refer to the legislation on the contract system and on the procurement of goods, works, services by certain types of legal entities in the qualification of abuse of official powers and their excess arises when determining the content of the signs of the subject and almost all the signs of the objective side of the deed. Industry legislation in the context under consideration is characterized by high dynamism, “layering”, a significant number of contradictions and shortcomings. These circumstances determine errors and lack of uniformity in judicial practice when distinguishing crimes provided for in Articles 285 of the Criminal Code and 286 of the Criminal Code when they are committed in the field of public procurement. Homogeneous, and in some cases identical criminal actions of customer officials – violations in the pricing of goods, works, services; actions restricting competition (inaction); violations of the established procedure for concluding (changing, terminating) state and municipal contracts; violations in the acceptance of delivered goods (work performed, services rendered), etc. – may receive different criminal legal assessment. The purpose of the article is to develop recommendations and criteria for distinguishing crimes provided for in Articles 285 of the Criminal Code of the Russian Federation and 286 of the Criminal Code of the Russian Federation, taking into account the peculiarities of criminal legal assessment when committing these acts in the field of public procurement. To achieve this goal, general scientific (analysis, synthesis, induction, deduction) and private scientific (formal legal) methods of cognition were used. In the study, taking into account the recommendations of the Supreme Court of the Russian Federation, theoretical positions in the science of criminal law, the peculiarities of the legal regulation of public procurement, recommendations for distinguishing the crimes under consideration, taking into account the specifics of the situation of their commission, are formulated.

PMRC: Prompt-Based Machine Reading Comprehension for Few-Shot Named Entity Recognition

The prompt-based method has been proven effective in improving the performance of pre-trained language models (PLMs) on sentence-level few-shot tasks. However, when applying prompting to token-level tasks such as Named Entity Recognition (NER), specific templates need to be designed, and all possible segments of the input text need to be enumerated. These methods have high computational complexity in both training and inference processes, making them difficult to apply in real-world scenarios. To address these issues, we redefine the NER task as a Machine Reading Comprehension (MRC) task and incorporate prompting into the MRC framework. Specifically, we sequentially insert boundary markers for various entity types into the templates and use these markers as anchors during the inference process to differentiate entity types. In contrast to the traditional multi-turn question-answering extraction in the MRC framework, our method can extract all spans of entity types in one round. Furthermore, we propose word-based template and example-based template that enhance the MRC framework's perception of entity start and end positions while significantly reducing the manual effort required for template design. It is worth noting that in cross-domain scenarios, PMRC does not require redesigning the model architecture and can continue training by simply replacing the templates to recognize entity types in the target domain. Experimental results demonstrate that our approach outperforms state-of-the-art models in low-resource settings, achieving an average performance improvement of +5.2% in settings where access to source domain data is limited. Particularly, on the ATIS dataset with a large number of entity types and 10-shot setting, PMRC achieves a performance improvement of +15.7%. Moreover, our method achieves a decoding speed 40.56 times faster than the template-based cloze-style approach.

Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains

Accurately typing entity mentions from text segments is a fundamental task for various natural language processing applications. Many previous approaches rely on massive human-annotated data to perform entity typing. Nevertheless, collecting such data in highly specialized science and engineering domains (e.g., software engineering and security) can be time-consuming and costly, without mentioning the domain gaps between training and inference data if the model needs to be applied to confidential datasets. In this paper, we study the task of seed-guided fine-grained entity typing in science and engineering domains, which takes the name and a few seed entities for each entity type as the only supervision and aims to classify new entity mentions into both seen and unseen types (i.e., those without seed entities). To solve this problem, we propose SEType which first enriches the weak supervision by finding more entities for each seen type from an unlabeled corpus using the contextualized representations of pre-trained language models. It then matches the enriched entities to unlabeled text to get pseudo-labeled samples and trains a textual entailment model that can make inferences for both seen and unseen types. Extensive experiments on two datasets covering four domains demonstrate the effectiveness of SEType in comparison with various baselines. Code and data are available at: https://github.com/yuzhimanhua/SEType.

Unify Named Entity Recognition Scenarios via Contrastive Real-Time Updating Prototype

Supervised named entity recognition (NER) aims to classify entity mentions into a fixed number of pre-defined types. However, in real-world scenarios, unknown entity types are continually involved. Naive fine-tuning will result in catastrophic forgetting on old entity types. Existing continual methods usually depend on knowledge distillation to alleviate forgetting, which are less effective on long task sequences. Moreover, most of them are specific to the class-incremental scenario and cannot adapt to the online scenario, which is more common in practice. In this paper, we propose a unified framework called Contrastive Real-time Updating Prototype (CRUP) that can handle different scenarios for NER. Specifically, we train a Gaussian projection model by a regularized contrastive objective. After training on each batch, we store the mean vectors of representations belong to new entity types as their prototypes. Meanwhile, we update existing prototypes belong to old types only based on representations of the current batch. The final prototypes will be used for the nearest class mean classification. In this way, CRUP can handle different scenarios through its batch-wise learning. Moreover, CRUP can alleviate forgetting in continual scenarios only with current data instead of old data. To comprehensively evaluate CRUP, we construct extensive benchmarks based on various datasets. Experimental results show that CRUP significantly outperforms baselines in continual scenarios and is also competitive in the supervised scenario.

Three Heads Are Better than One: Improving Cross-Domain NER with Progressive Decomposed Network

Cross-domain named entity recognition (NER) tasks encourage NER models to transfer knowledge from data-rich source domains to sparsely labeled target domains. Previous works adopt the paradigms of pre-training on the source domain followed by fine-tuning on the target domain. However, these works ignore that general labeled NER source domain data can be easily retrieved in the real world, and soliciting more source domains could bring more benefits. Unfortunately, previous paradigms cannot efficiently transfer knowledge from multiple source domains. In this work, to transfer multiple source domains' knowledge, we decouple the NER task into the pipeline tasks of mention detection and entity typing, where the mention detection unifies the training object across domains, thus providing the entity typing with higher-quality entity mentions. Additionally, we request multiple general source domain models to suggest the potential named entities for sentences in the target domain explicitly, and transfer their knowledge to the target domain models through the knowledge progressive networks implicitly. Furthermore, we propose two methods to analyze in which source domain knowledge transfer occurs, thus helping us judge which source domain brings the greatest benefit. In our experiment, we develop a Chinese cross-domain NER dataset. Our model improved the F1 score by an average of 12.50% across 8 Chinese and English datasets compared to models without source domain data.

SeqGPT: An Out-of-the-Box Large Language Model for Open Domain Sequence Understanding

Large language models (LLMs) have shown impressive abilities for open-domain NLP tasks. However, LLMs are sometimes too footloose for natural language understanding (NLU) tasks which always have restricted output and input format. Their performances on NLU tasks are highly related to prompts or demonstrations and are shown to be poor at performing several representative NLU tasks, such as event extraction and entity typing. To this end, we present SeqGPT, a bilingual (i.e., English and Chinese) open-source autoregressive model specially enhanced for open-domain natural language understanding. We express all NLU tasks with two atomic tasks, which define fixed instructions to restrict the input and output format but still ``open'' for arbitrarily varied label sets. The model is first instruction-tuned with extremely fine-grained labeled data synthesized by ChatGPT and then further fine-tuned by 233 different atomic tasks from 152 datasets across various domains. The experimental results show that SeqGPT has decent classification and extraction ability, and is capable of performing language understanding tasks on unseen domains. We also conduct empirical studies on the scaling of data and model size as well as on the transfer across tasks. Our models are accessible at https://github.com/Alibaba-NLP/SeqGPT.

Robust Few-Shot Named Entity Recognition with Boundary Discrimination and Correlation Purification

Few-shot named entity recognition (NER) aims to recognize novel named entities in low-resource domains utilizing existing knowledge. However, the present few-shot NER models assume that the labeled data are all clean without noise or outliers, and there are few works focusing on the robustness of the cross-domain transfer learning ability to textual adversarial attacks in Few-shot NER. In this work, we comprehensively explore and assess the robustness of few-shot NER models under textual adversarial attack scenario, and found the vulnerability of existing few-shot NER models. Furthermore, we propose a robust two-stage few-shot NER method with Boundary Discrimination and Correlation Purification (BDCP). Specifically, in the span detection stage, the entity boundary discriminative module is introduced to provide a highly distinguishing boundary representation space to detect entity spans. In the entity typing stage, the correlations between entities and contexts are purified by minimizing the interference information and facilitating correlation generalization to alleviate the perturbations caused by textual adversarial attacks. In addition, we construct adversarial examples for few-shot NER based on public datasets Few-NERD and Cross-Dataset. Comprehensive evaluations on those two groups of few-shot NER datasets containing adversarial examples demonstrate the robustness and superiority of the proposed method.

ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and Context

Named entity recognition (NER) aims to identify and classify specific entities mentioned in textual sentences. Most existing superior NER models employ the standard fully supervised paradigm, which requires a large amount of annotated data during training. In order to maintain performance with insufficient annotation resources (i.e., low resources), in-context learning (ICL) has drawn a lot of attention, due to its plug-and-play nature compared to other methods (e.g., meta-learning and prompt learning). In this manner, how to retrieve high-correlated demonstrations for target sentences serves as the key to emerging ICL ability. For the NER task, the correlation implies the consistency of both ontology (i.e., generalized entity type) and context (i.e., sentence semantic), which is ignored by previous NER demonstration retrieval techniques. To address this issue, we propose ConsistNER, a novel three-stage framework that incorporates ontological and contextual information for low-resource NER. Firstly, ConsistNER employs large language models (LLMs) to pre-recognize potential entities in a zero-shot manner. Secondly, ConsistNER retrieves the sentence-specific demonstrations for each target sentence based on the two following considerations: (1) Regarding ontological consistency, demonstrations are filtered into a candidate set based on ontology distribution. (2) Regarding contextual consistency, an entity-aware self-attention mechanism is introduced to focus more on the potential entities and semantic-correlated tokens. Finally, ConsistNER feeds the retrieved demonstrations for all target sentences into LLMs for prediction. We conduct experiments on four widely-adopted NER datasets, including both general and specific domains. Experimental results show that ConsistNER achieves a 6.01%-26.37% and 3.07%-21.18% improvement over the state-of-the-art baselines on Micro-F1 scores under 1- and 5-shot settings, respectively.

Medical knowledge graph completion via fusion of entity description and type information

Medical Knowledge Graphs (MKGs) are vital in propelling big data technologies in healthcare and facilitating the realization of medical intelligence. However, large-scale MKGs often exhibit characteristics of data sparsity and missing facts. Following the latest advances, knowledge embedding addresses these problems by performing knowledge graph completion. Most knowledge embedding algorithms rely solely on triplet structural information, overlooking the rich information hidden within entity property sets, leading to bottlenecks in performance enhancement when dealing with the intricate relations of MKGs. Inspired by the semantic sensitivity and explicit type constraints unique to the medical domain, we propose BioBERT-based graph embedding model. This model represents an evolvable framework that integrates graph embedding, language embedding, and type information, thereby optimizing the utility of MKGs. Our study utilizes not only WordNet as a benchmark dataset but also incorporates MedicalKG to compare and corroborate the specificity of medical knowledge. Experimental results on these datasets indicate that the proposed fusion framework achieves state-of-art (SOTA) performance compared to other baselines. We believe that this incremental improvement provides promising insights for future medical knowledge graph completion endeavors.