Entity Relation Extraction Research Articles

Abstract 5366: Constructing the largest-scale biomedical knowledge graph using all PubMed articles and its application in automated knowledge discovery

Abstract The number of biomedical publications is growing at an accelerated speed. This ever-increasing amount of scientific literature has made reading all the published articles regularly impossible even for a very specific research area. A solid grasp of existing literature is essential for coming out with novel and plausible scientific ideas. To bridge the gap between the published scientific findings and our incapability of manually processing them, we need to convert the unstructured text into structured form to enable automated methods to use the structured, machine-readable information to generate novel hypotheses, which can then be manually validated. A plausible approach for converting unstructured text into structured form is to use named entity recognition (NER) and relation extraction (RE) methods to identify the biological entities and extract their relations to construct knowledge graphs (KGs). KGs can link concepts within existing research to allow researchers to find connections that may have been difficult to discover without them. The LitCoin Natural Language Processing (NLP) Challenge was recently organized by NCATS of NIH and NASA to spur innovation by rewarding the most creative and high-impact uses of biomedical, publication-free text to create KGs. Our team participated in the challenge and ranked first place. Using the pipelines developed for the LitCoin NLP challenge, we have constructed the largest-scale biomedical KG using all PubMed articles. We further develop advanced deep-learning methods to predict new links from the constructed KG. We demonstrate the power of this new framework using several examples important for drug discovery. Citation Format: Yuan Zhang, Feng Pan, Xin Sui, Donghu Sun, Menghan Chung, Jinfeng Zhang. Constructing the largest-scale biomedical knowledge graph using all PubMed articles and its application in automated knowledge discovery. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5366.

Abstract 5421: Constructing the largest-scale knowledge graph using all PubMed abstracts and its application for highly specific and accurate knowledge retrieval

Abstract Most of the biomedical knowledge the research community has acquired during the past few decades has been deposited in scientific literature as unstructured text. Converting the unstructured text into the structured form will enable novel methodologies and applications for scientific discovery that can fully harness the power of the existing knowledge. To this end, two fundamental questions need to be addressed: named entity recognition (NER) and relation extraction (RE). NER deals with identifying the concepts or entities in texts, such as diseases, genes/proteins, chemical compounds, etc. while RE aims to extract the relations among these entities. Together, the extracted information forms a knowledge graph (KG) where the nodes are entities in the texts and the edges represent their relationships. KGs can link concepts within existing research to allow researchers to find connections that may have been difficult to discover without them. The LitCoin Natural Language Processing (NLP) Challenge was recently organized by NCATS of NIH and NASA to spur innovation by rewarding the most creative and high-impact uses of biomedical text to create KGs. Our team participated in the challenge and ranked first place. We have applied the methods we developed for the LitCoin NLP challenge to all PubMed abstracts and constructed the largest-scale biomedical KG to date. We show that powerful and versatile query functions can be implemented on top of the KG to enable highly specific and accurate knowledge retrieval and inference of causal and indirect relationships. Citation Format: Xin Sui, Yuan Zhang, Feng Pan, Donghu Sun, Menghan Chung, Jinfeng Zhang. Constructing the largest-scale knowledge graph using all PubMed abstracts and its application for highly specific and accurate knowledge retrieval. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5421.

Web Application for Interpretation of Doctor's Handwritten Prescription and Suggesting the best Price Offer over Various e-Commerce Websites using AI

Patient record-keeping is crucial for accurate diagnoses and treatment. In India, due to time constraints, most doctors manually write prescriptions, making it challenging for pharmacists to read them correctly. This increases the risk of dispensing the wrong medicine, which can have serious and even fatal consequences for patients. To address this problem, this research proposes an online handwritten medical prescription recognition system that allows users to scan prescriptions and compare prices across different websites. OCR techniques are used to recognize medicine names in handwritten prescriptions, while NLP techniques such as Cosine Similarity are employed to overcome the issue of misinterpretation. The review study focuses on Named Entity Recognition and Relation Extraction, which help identify named entities and extract relations between entities. Most state-of-the-art techniques are offline and computationally expensive, highlighting the need for understanding the deep-learning processes used in the proposed system. The system stores various features such as medicine names, uploaded images, user details, and search history to improve recognition accuracy. Additionally, new features are proposed to enhance accuracy further. Uses a local dataset from a pharmacy shop and past prescription records from local doctors.

A Novel Chinese Overlapping Entity Relation Extraction Model Using Word-Label Based on Cascade Binary Tagging

In recent years, overlapping entity relation extraction has received a great deal of attention and has made good progress in English. However, the research on overlapping entity relation extraction in Chinese still faces two key problems: one is the lack of datasets with overlapping entity instances, and the other is the lack of a neural network model that can effectively solve overlapping entity relation extraction. To address the above problems, this paper produces an interpersonal relationship dataset, NewsPer, for news texts and proposes a Chinese overlapping entity relation extraction model, DepCasRel. First, the model uses “Word-label” to incorporate the character features of Chinese text into the dependency analysis graph, and then uses the same binary labeling method to label the head and tail entities embedded in the text. Finally, the text’s triples are extracted. DepCasRel solves the problem that traditional methods make it difficult to extract triples with overlapping entities. Experiments on our manually annotated dataset NewsPer show that DepCasRel can effectively encode the semantic and structural information of text and improve the performance of an overlapping entity relation extraction model.

Hybrid Decision-Making-Method-Based Intelligent System for Integrated Bogie Welding Manufacturing

To address the challenges of incomplete knowledge representation, independent decision ranges, and insufficient causal decisions in bogie welding decisions, this paper proposes a hybrid decision-making method and develops a corresponding intelligent system. The collaborative case, rule, and knowledge graph approach is used to support structured documents and domain causality decisions. In addition, we created a knowledge model of bogie welding characteristics and proposed a case-matching method based on empirical weights. Several entity categorizations and relationship extraction models were trained under supervised conditions while building the knowledge graph. CRF and CR-CNN obtained high combined F1 scores (0.710 for CRF and 0.802 for CR-CNN) in the entity classification and relationship extraction tasks, respectively. We designed and developed an intelligent decision system based on the proposed method to implement engineering applications. This system was validated with some actual engineering data. The results show that the system obtained a high score on the accuracy test (0.947 for Corrected Accuracy) and can effectively complete structured document and causality decision-making tasks, having large research significance and engineering value.

Joint learning-based causal relation extraction from biomedical literature

Causal relation extraction of biomedical entities is one of the most complex tasks in biomedical text mining, which involves two kinds of information: entity relations and entity functions. One feasible approach is to take relation extraction and function detection as two independent sub-tasks. However, this separate learning method ignores the intrinsic correlation between them and leads to unsatisfactory performance. In this paper, we propose a joint learning model, which combines entity relation extraction and entity function detection to exploit their commonality and capture their inter-relationship, so as to improve the performance of biomedical causal relation extraction. Experimental results on the BioCreative-V Track 4 corpus show that our joint learning model outperforms the separate models in BEL statement extraction, achieving the F1 scores of 57.0% and 37.3% on the test set in Stage 2 and Stage 1 evaluations, respectively. This demonstrates that our joint learning system reaches the state-of-the-art performance in Stage 2 compared with other systems.

COVID‐19 clinical medical relationship extraction based on MPNet

AbstractWith the rapid development of biomedical research and information technology, the number of clinical medical literature has increased exponentially. At present, COVID‐19 clinical text research has some problems, such as lack of corpus and poor annotation quality. In clinical medical literature, there are many medical related semantic relationships between entities. After the task of entity recognition, how to further extract the relationships between entities efficiently and accurately becomes very critical. In this study, a COVID‐19 clinical trial data relationship extraction model based on deep learning method is proposed. The model adopts MPNet model, bidirectional‐GRU (BiGRU) network, MAtt mechanism and Conditional Random Field inference layer integration architecture and improves the problem that static word vector cannot represent ambiguity through pre‐trained language model. BiGRU network is used to replace the current Bi directional long short term memory structure and simplify the network structure of Long Short Term Memory to improve the training efficiency of the model. Through comparative experiments, the proposed method performs well in the COVID‐19 clinical text entity relation extraction task.

Span-based single-stage joint entity-relation extraction model.

Extracting entities and relations from the unstructured text has attracted increasing attention in recent years. The existing work has achieved considerable results, yet it is difficult to solve entity overlap and exposure bias. To address cascading errors, exposure bias, and entity overlap in existing entity relation extraction approaches, we propose a joint entity relation extraction model (SMHS) based on a span-level multi-head selection mechanism, transforming entity relation extraction into a span-level multi-head selection problem. Our model uses span-tagger and span-embedding to construct span semantic vectors, utilizes LSTM and multi-head self-attention mechanism for span feature extraction, multi-head selection mechanism for span-level relation decoding, and introduces span classification task for multi-task learning to decode out the relation triad in a single-stage. Experiments on the classic English dataset NYT and the publicly available Chinese relationship extraction dataset DuIE 2.0 show that this method achieves better results than the baseline method, which verifies the effectiveness of this method. Source code and data are published here(https://github.com/Beno-waxgourd/NLP.git).

Construction and evaluation of a domain-specific knowledge graph for knowledge discovery

PurposeThis study aims to evaluate a method of building a biomedical knowledge graph (KG).Design/methodology/approachThis research first constructs a COVID-19 KG on the COVID-19 Open Research Data Set, covering information over six categories (i.e. disease, drug, gene, species, therapy and symptom). The construction used open-source tools to extract entities, relations and triples. Then, the COVID-19 KG is evaluated on three data-quality dimensions: correctness, relatedness and comprehensiveness, using a semiautomatic approach. Finally, this study assesses the application of the KG by building a question answering (Q&A) system. Five queries regarding COVID-19 genomes, symptoms, transmissions and therapeutics were submitted to the system and the results were analyzed.FindingsWith current extraction tools, the quality of the KG is moderate and difficult to improve, unless more efforts are made to improve the tools for entity extraction, relation extraction and others. This study finds that comprehensiveness and relatedness positively correlate with the data size. Furthermore, the results indicate the performances of the Q&A systems built on the larger-scale KGs are better than the smaller ones for most queries, proving the importance of relatedness and comprehensiveness to ensure the usefulness of the KG.Originality/valueThe KG construction process, data-quality-based and application-based evaluations discussed in this paper provide valuable references for KG researchers and practitioners to build high-quality domain-specific knowledge discovery systems.

Span-Based Fine-Grained Entity-Relation Extraction via Sub-Prompts Combination

With the development of information extraction technology, a variety of entity-relation extraction paradigms have been formed. However, approaches guided by these existing paradigms suffer from insufficient information fusion and too coarse extraction granularity, leading to difficulties extracting all triples in a sentence. Moreover, the joint entity-relation extraction model cannot easily adapt to the relation extraction task. Therefore, we need to design more fine-grained and flexible extraction methods. In this paper, we propose a new extraction paradigm based on existing paradigms. Then, based on it, we propose SSPC, a method for Span-based Fine-Grained Entity-Relation Extraction via Sub-Prompts Combination. SSPC first decomposes the task into three sub-tasks, namely S,R Extraction, R,O Extraction and S,R,O Classification and then uses prompt tuning to fully integrate entity and relation information in each part. This fine-grained extraction framework makes the model easier to adapt to other similar tasks. We conduct experiments on joint entity-relation extraction and relation extraction, respectively. The experimental results show that our model outperforms previous methods and achieves state-of-the-art results on ADE, TACRED, and TACREV.

Joint entity–relation extraction for natural disaster based on table filling

In this article, we propose a joint extraction of entity–relation triplets in natural disaster cases based on word pair relation table filling. For computational accuracy concerns or other reasons, traditional works often do entity recognition and relation extraction separately; it might put less attention over the task connections and triplet global association. We propose the Global Table Attention GRU (GL-TGRU) model as a joint approach that uses sequence information encoding and table information encoding to jointly learn the representation and enhance the global association of entity and relation in table filling. We evaluated the proposed model on the public data set SciERC and the natural disaster data set SSD-HDS, respectively. The F1 scores of experimental results of the GL-TGRU model for entity identification and relation extraction achieved 65.81% and 37.30% on SciERC and achieved 93.89% and 84.06% on SSD-HDS. The results show our model helps to capture more global association relations of entity and relation, which can better identify the entity–relation triplet information.

A Levenshtein distance-based method for word segmentation in corpus augmentation of geoscience texts

ABSTRACT For geoscience text, rich domain corpora have become the basis of improving the model performance in word segmentation. However, the lack of domain-specific corpus with annotation labelled has become a major obstacle to professional information mining in geoscience fields. In this paper, we propose a corpus augmentation method based on Levenshtein distance. According to the technique, a geoscience dictionary of 20,137 words was collected and constructed by crawling the keywords from published papers in China National Knowledge Infrastructure (CNKI). The dictionary was further used as the main source of synonyms to enrich the geoscience corpus according to the Levenshtein distance between words. Finally, a Chinese word segmentation model combining the BERT, Bi-gated recurrent neural network (Bi-GRU), and conditional random fields (CRF) was implemented. Geoscience corpus composed of complex long specific vocabularies has been selected to test the proposed word segmentation framework. CNN-LSTM, Bi-LSTM-CRF, and Bi-GRU-CRF models were all selected to evaluate the effects of Levenshtein data augmentation technique. Experiments results prove that the proposed methods achieve a significant performance improvement of more than 10%. It has great potential for natural languages processing tasks like named entity recognition and relation extraction.

TSVFN: Two-Stage Visual Fusion Network for multimodal relation extraction

Multimodal relation extraction is a critical task in information extraction, aiming to predict the class of relations between head and tail entities from linguistic sequences and related images. However, the current works are vulnerable to less relevant visual objects detected from images and are not able to sufficiently fuse visual information into text pre-trained models. To overcome these problems, we propose a Two-Stage Visual Fusion Network (TSVFN) that employs the multimodal fusion approach in vision-enhanced entity relation extraction. In the first stage, we design multimodal graphs, whose novelty lies mainly in transforming the sequence learning into the graph learning. In the second stage, we merge the transformer-based visual representation into the text pre-trained model by a multi-scale cross-model projector. Specifically, two multimodal fusion operations are implemented inside the pre-trained model respectively. We finally accomplish deep interaction of multimodal multi-structured data in two fusion stages. Extensive experiments are conducted on a dataset (MNRE), our model outperforms the current state-of-the-art method by 1.76%, 1.52%, 1.29%, and 1.17% in terms of accuracy, precision, recall, and F1 score, respectively. Moreover, our model also achieves excellent results under the condition of fewer samples.

Negation-based transfer learning for improving biomedical Named Entity Recognition and Relation Extraction

Background and Objectives:Named Entity Recognition (NER) and Relation Extraction (RE) are two of the most studied tasks in biomedical Natural Language Processing (NLP). The detection of specific terms and entities and the relationships between them are key aspects for the development of more complex automatic systems in the biomedical field. In this work, we explore transfer learning techniques for incorporating information about negation into systems performing NER and RE. The main purpose of this research is to analyse to what extent the successful detection of negated entities in separate tasks helps in the detection of biomedical entities and their relationships. Methods:Three neural architectures are proposed in this work, all of them mainly based on Bidirectional Long Short-Term Memory (Bi-LSTM) networks and Conditional Random Fields (CRFs). While the first architecture is devoted to detecting triggers and scopes of negated entities in any domain, two specific models are developed for performing isolated NER tasks and joint NER and RE tasks in the biomedical domain. Then, weights related to negation detection learned by the first architecture are incorporated into those last models. Two different languages, Spanish and English, are taken into account in the experiments. Results:Performance of the biomedical models is analysed both when the weights of the neural networks are randomly initialized, and when weights from the negation detection model are incorporated into them. Improvements of around 3.5% of F-Measure in the English language and more than 7% in the Spanish language are achieved in the NER task, while the NER+RE task increases F-Measure scores by more than 13% for the NER submodel and around 2% for the RE submodel. Conclusions:The obtained results allow us to conclude that negation-based transfer learning techniques are appropriate for performing biomedical NER and RE tasks. These results highlight the importance of detecting negation for improving the identification of biomedical entities and their relationships. The explored techniques show robustness by maintaining consistent results and improvements across different tasks and languages.

Exploring named entity recognition and relation extraction for ontology and medical records integration

The available natural language data in electronic health records is of noteworthy interest to health research and development. Nevertheless, their manual analysis is not feasible and poses a challenge to accessing valuable information in these records. This paper presents an approach to automatically extract information from these unstructured medical records using Domain Entity Recognition and Relation Extraction, structuring the results through a domain ontology. We developed our work in the oncology domain, an attention-demanding field. The main contribution of this work lies in integrating multiple resources in a complete methodology to accomplish this task. We developed a new entity and relation annotated dataset of medical evolutions in Brazilian Portuguese, containing 1622 documents, 146,769 entities, and 111,716 relations. We attained 78.24 % accuracy for entity and relation extraction in the exams domain. Healthcare specialists evaluated the approach regarding entity recognition and relation extraction positively and considered the methodology valuable to health professionals.

Entity relationship extraction from Chinese electronic medical records based on feature augmentation and cascade binary tagging framework.

Extracting entity relations from unstructured Chinese electronic medical records is an important task in medical information extraction. However, Chinese electronic medical records mostly have document-level volumes, and existing models are either unable to handle long text sequences or exhibit poor performance. This paper proposes a neural network based on feature augmentation and cascade binary tagging framework. First, we utilize a pre-trained model to tokenize the original text and obtain word embedding vectors. Second, the word vectors are fed into the feature augmentation network and fused with the original features and position features. Finally, the cascade binary tagging decoder generates the results. In the current work, we built a Chinese document-level electronic medical record dataset named VSCMeD, which contains 595 real electronic medical records from vascular surgery patients. The experimental results show that the model achieves a precision of 87.82% and recall of 88.47%. It is also verified on another Chinese medical dataset CMeIE-V2 that the model achieves a precision of 54.51% and recall of 48.63%.

Food safety in health: a model of extraction for food contaminants.

Contaminants are the critical targets of food safety supervision and risk assessment. In existing research, food safety knowledge graphs are used to improve the efficiency of supervision since they supply the relationship between contaminants and foods. Entity relationship extraction is one of the crucial technologies of knowledge graph construction. However, this technology still faces the issue of single entity overlap. This means that a head entity in a text description may have multiple corresponding tail entities with different relationships. To address this issue, this work proposes a pipeline model with neural networks for multiple relations enhanced entity pairs extraction. The proposed model can predict the correct entity pairs in terms of specific relations by introducing the semantic interaction between relation identification and entity extraction. We conducted various experiments on our own dataset FC and on the open public available data set DuIE2.0. The results of experiments show our model reaches the state-of-the-art, and the case study indicates our model can correctly extract entity-relationship triplets to release the problem of single entity overlap.

A smart conflict resolution model using multi-layer knowledge graph for conceptual design

Reducing the impact of conflicts on requirement-function-structure mapping in the early stage of product design is an important measure to achieve conceptual innovation, which relies on accurate reasoning of multi-domain knowledge. As product requirements become more personalized and diverse, traditional discrete knowledge organization and reasoning methods are difficult to adapt to the challenges of continuity and precision in conceptual solution. Knowledge graphs with complex networks have obvious advantages in association detection, knowledge visualization, and explainable reasoning of implicit knowledge, which offer innovative opportunities for conflict resolution in conceptual design. Therefore, a smart conflict resolution model using a multi-layer Knowledge Graph for Conceptual Design(mKGCD) is proposed in this study. A knowledge expression form of FBS-oriented design patent vocabulary is proposed, which is used for knowledge entity recognition and relation extraction based on natural language processing. A label mapping method based on inventive principles is used for patent classification and a four-layer semantic network for conflict resolution is constructed. Through semantic distance calculation, the designer's requirements for function/behavior/structure are smart deployed to obtain appropriate knowledge. A case study of the conceptual design of a collapsible installation and handling equipment demonstrates the feasibility of the proposed approach. The proposed method can not only meet the functional solution and innovation in the context of different design requirements, but also effectively improve the design efficiency in the iterative design process by means of multiple meanings of one graph.

Digital ECMT Cancer Trial Matching Tool: an Open Source Research Application to Support Oncologists in the Identification of Precision Medicine Clinical Trials.

Matching patients with cancer to precision medicine clinical trials on the basis of their tumor genotype has the potential to improve outcomes for patients who have exhausted standard-of-care treatment options. However, the matching process presents a substantial challenge because of the number of clinical trials available. We describe a free, open source research tool designed to extract relevant trial information to support oncologists in the matching process, and we illustrate its utility with recent case studies of patients who were matched to trials using this tool. Trial records are sourced from ClinicalTrials.gov and indexed using natural language processing techniques, including named entity recognition, term normalization, and relationship extraction. Relationships between trials and genetic alterations are assigned scores on the basis of a rule-based system. All data are updated daily. A user interface is provided via R Shiny app. An instance of the trial match tool, configured for UK clinical trials, is hosted by the digital Experimental Cancer Medicine Team (see link in Data Sharing Statement). Users select the relevant cancer type and genetic alteration(s). Matching studies are ranked according to the score assigned for the selected genetic alterations. Results may be downloaded and attached to the patient's health record if desired. The tool is currently being used to support the ongoing TARGET National study, which aims to match up to 6,000 patients to early phase clinical trials. We present three case studies that exemplify relationships between genetic alterations and studies. With increasing numbers of precision medicine treatments and as comprehensive molecular profiling of tumor samples becomes more common, decision support tools are likely to become increasingly important. This work represents an important step toward the development and wider implementation of such systems.

A Weakly-Supervised Method for Named Entity Recognition of Agricultural Knowledge Graph

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.