Entity Linking Research Articles

Identifying Notable Tuples in Multi-Concept Web Tables

Identifying notable tuples in a web table is of great help for table understanding and table summarization. However, existing document-internal feature-based methods are inappropriate for identifying notable tuples in web tables. Additionally, for the web table describing multiple concepts, the notability evaluation of a tuple needs to take into account multiple entities as well as their importance in this tuple. In this paper, we investigate the task of identifying notable tuples in a multi-concept web table and propose a framework that includes three tasks: (1) identify multiple entity columns and their importance weights by building a column correlation graph based on types and relationships in the table; (2) obtain fine-grained entity notability scores based on entity link graph and provide solution for entity link failure and entity domain neglection; and (3) evaluate tuple notability by a weighted sum of notability scores of all entities in the tuple. Comprehensive evaluation of our approach is based on real-world web tables. The results demonstrate that our approach outperforms the state-of-the-art baselines by 4.6% on the precision of detecting multiple entity columns and by 12.5% on the metric normalized discounted cumulative gain (NDCG) of evaluating entity notability.

Candidate Set Expansion for Entity and Relation Linking Based on Mutual Entity–Relation Interaction

Entity and relation linking are the core tasks in knowledge base question answering (KBQA). They connect natural language questions with triples in the knowledge base. In most studies, researchers perform these two tasks independently, which ignores the interplay between the entity and relation linking. To address the above problems, some researchers have proposed a framework for joint entity and relation linking based on feature joint and multi-attention. In this paper, based on their method, we offer a candidate set generation expansion model to improve the coverage of correct candidate words and to ensure that the correct disambiguation objects exist in the candidate list as much as possible. Our framework first uses the initial relation candidate set to obtain the entity nodes in the knowledge graph related to this relation. Second, the filtering rule filters out the less-relevant entity candidates to obtain the expanded entity candidate set. Third, the relation nodes directly connected to the nodes in the expanded entity candidate set are added to the initial relation candidate set. Finally, a ranking algorithm filters out the less-relevant relation candidates to obtain the expanded relation candidate set. An empirical study shows that this model improves the recall and correctness of the entity and relation linking for KBQA. The candidate set expansion method based on entity–relation interaction proposed in this paper is highly portable and scalable. The method in this paper considers the connections between question subgraphs in knowledge graphs and provides new ideas for the candidate set expansion.

Explainable clinical coding with in-domain adapted transformers

Background and ObjectiveAutomatic clinical coding is a crucial task in the process of extracting relevant information from unstructured medical documents contained in Electronic Health Records (EHR). However, most of the existing computer-based methods for clinical coding act as “black boxes”, without giving a detailed description of the reasons for the clinical-coding assignments, which greatly limits their applicability to real-world medical scenarios. The objective of this study is to use transformer-based models to effectively tackle explainable clinical-coding. In this way, we require the models to perform the assignments of clinical codes to medical cases, but also to provide the reference in the text that justifies each coding assignment. MethodsWe examine the performance of 3 transformer-based architectures on 3 different explainable clinical-coding tasks. For each transformer, we compare the performance of the original general-domain version with an in-domain version of the model adapted to the specificities of the medical domain. We address the explainable clinical-coding problem as a dual medical named entity recognition (MER) and medical named entity normalization (MEN) task. For this purpose, we have developed two different approaches, namely a multi-task and a hierarchical-task strategy. ResultsFor each analyzed transformer, the clinical-domain version significantly outperforms the corresponding general domain model across the 3 explainable clinical-coding tasks analyzed in this study. Furthermore, the hierarchical-task approach yields a significantly superior performance than the multi-task strategy. Specifically, the combination of the hierarchical-task strategy with an ensemble approach leveraging the predictive capabilities of the 3 distinct clinical-domain transformers, yields the best obtained results, with f1-score, precision and recall of 0.852, 0.847 and 0.849 on the Cantemist-Norm task and 0.718, 0.566 and 0.633 on the CodiEsp-X task, respectively. ConclusionsBy separately addressing the MER and MEN tasks, as well as by following a context-aware text-classification approach to tackle the MEN task, the hierarchical-task approach effectively reduces the intrinsic complexity of explainable clinical-coding, leading the transformers to establish new SOTA performances for the predictive tasks considered in this study. In addition, the proposed methodology has the potential to be applied to other clinical tasks that require both the recognition and normalization of medical entities.

Improving Entity Linking in Chinese Domain by Sense Embedding Based on Graph Clustering

Improving Entity Linking in Chinese Domain by Sense Embedding Based on Graph Clustering

LDAViewer: An Automatic Language-Agnostic System for Discovering State-of-the-Art Topics in Research Using Topic Modeling, Bidirectional Encoder Representations From Transformers, and Entity Linking

LDAViewer: An Automatic Language-Agnostic System for Discovering State-of-the-Art Topics in Research Using Topic Modeling, Bidirectional Encoder Representations From Transformers, and Entity Linking

Edge Weight Updating Neural Network for Named Entity Normalization.

Discriminating the matched named entity pairs or identifying the entities' canonical forms are critical in text mining tasks. More precise named entity normalization in text mining will benefit other subsequent text analytic applications. We built the named entity normalization model with a novel edge weight updating neural network. We, next, verify our model's performance on NCBI disease, BC5CDR disease, and BC5CDR chemical databases, which are widely used named entity normalization datasets in the bioinformatics field. We also tested our model with our own financial named entity normalization dataset to validate the efficacy for more general applications. Using the constructed dataset, we differentiate named entity pairs. Our model achieved the highest named entity normalization performances in terms of various evaluation metrics. Our proposed model when tested on four different datasets achieved state-of-the-art results.

Instance level analysis on linked open data connectivity for cultural heritage entity linking and data integration

In cultural heritage, many projects execute Named Entity Linking (NEL) through global Linked Open Data (LOD) references in order to identify and disambiguate entities in their local datasets. It allows users to obtain extra information and contextualise the data with it. Thus, the aggregation and integration of heterogeneous LOD are expected. However, such development is still limited partly due to data quality issues. In addition, analysis on the LOD quality has not sufficiently been conducted for cultural heritage. Moreover, most research on data quality concentrates on ontology and corpus level observations. This paper examines the quality of the eleven major LOD sources used for NEL in cultural heritage with an emphasis on instance-level connectivity and graph traversals. Standardised linking properties are inspected for 100 instances/entities in order to create traversal route maps. Other properties are also assessed for quantity and quality. The outcomes suggest that the LOD is not fully interconnected and centrally condensed; the quantity and quality are unbalanced. Therefore, they cast doubt on the possibility of automatically identifying, accessing, and integrating known and unknown datasets. This implies the need for LOD improvement, as well as the NEL strategies to maximise the data integration.

Biomedical named entity normalization via interaction-based synonym marginalization

ObjectiveBiomedical named entity normalization (BNEN) is a fundamental natural language processing (NLP) task in the biomedical domain. Many representation learning-based methods have been successfully applied to BNEN in recent years. Most of them encode a given biomedical named entity mention (BNEM) and candidates separately, some of them consider relations between the BNEM and its candidates, however, few consider relations among the candidates, which may be useful for BNEN. Material and MethodsIn this paper, we propose a novel interaction-based synonym marginalization for BNEN, which can capture both the relations between a given mention and the mention’s candidates and that among the candidates, called IA-BIOSYN. In IA-BIOSYN, given a BNEM, a candidate selector is used to obtain the candidates of the BNEM dynamically, then an interaction module is used to model BNEM-candidate relations as well as candidate-candidate relations, and finally a synonym marginalization module is used to determine which candidate(s) the BNEM should be mapped to. To validate the effectiveness of our proposed method, we compare it with other state-of-the-art (SOTA) methods on three public BNEN datasets: NCBI-Disease, BC5CDR-Disease and BC5CDR-Chemical. ResultsOur proposed method achieves Acc@1 of 0.9333, 0.9379 and 0.9693 on NCBI-Disease, BC5CDR-Disease and BC5CDR-Chemical, respectively, significantly better than other SOTA methods. ConclusionsBoth the relations between a given BNEM and its candidates, and the relations among the candidates are useful for BNEN, and the proposed IA-BIOSYN can capture the two types of relations effectively.

How do others cope? Extracting coping strategies for adverse drug events from social media

Patients advise their peers on how to cope with their illness in daily life on online support groups. To date, no efforts have been made to automatically extract recommended coping strategies from online patient discussion groups. We introduce this new task, which poses a number of challenges including complex, long entities, a large long-tailed label space, and cross-document relations. We present an initial ontology for coping strategies as a starting point for future research on coping strategies, and the first end-to-end pipeline for extracting coping strategies for side effects. We also compared two possible computational solutions for this novel and highly challenging task; multi-label classification and named entity recognition (NER) with entity linking (EL). We evaluated our methods on the discussion forum from the Facebook group of the worldwide patient support organization ‘GIST support international’ (GSI); GIST support international donated the data to us. We found that coping strategy extraction is difficult and both methods attain limited performance (measured with F1 score) on held out test sets; multi-label classification outperforms NER+EL (F1=0.220 vs F1=0.155). An inspection of the multi-label classification output revealed that for some of the incorrect predictions, the reference label is close to the predicted label in the ontology (e.g. the predicted label ‘juice’ instead of the more specific reference label ‘grapefruit juice’). Performance increased to F1=0.498 when we evaluated at a coarser level of the ontology. We conclude that our pipeline can be used in a semi-automatic setting, in interaction with domain experts to discover coping strategies for side effects from a patient forum. For example, we found that patients recommend ginger tea for nausea and magnesium and potassium supplements for cramps. This information can be used as input for patient surveys or clinical studies.

A Probabilistic Data Fusion Modeling Approach for Extracting True Values from Uncertain and Conflicting Attributes

Real-world data obtained from integrating heterogeneous data sources are often multi-valued, uncertain, imprecise, error-prone, outdated, and have different degrees of accuracy and correctness. It is critical to resolve data uncertainty and conflicts to present quality data that reflect actual world values. This task is called data fusion. In this paper, we deal with the problem of data fusion based on probabilistic entity linkage and uncertainty management in conflict data. Data fusion has been widely explored in the research community. However, concerns such as explicit uncertainty management and on-demand data fusion, which can cope with dynamic data sources, have not been studied well. This paper proposes a new probabilistic data fusion modeling approach that attempts to find true data values under conditions of uncertain or conflicted multi-valued attributes. These attributes are generated from the probabilistic linkage and merging alternatives of multi-corresponding entities. Consequently, the paper identifies and formulates several data fusion cases and sample spaces that require further conditional computation using our computational fusion method. The identification is established to fit with a real-world data fusion problem. In the real world, there is always the possibility of heterogeneous data sources, the integration of probabilistic entities, single or multiple truth values for certain attributes, and different combinations of attribute values as alternatives for each generated entity. We validate our probabilistic data fusion approach through mathematical representation based on three data sources with different reliability scores. The validity of the approach was assessed via implementation into our probabilistic integration system to show how it can manage and resolve different cases of data conflicts and inconsistencies. The outcome showed improved accuracy in identifying true values due to the association of constructive evidence.

EAGS: An extracting auxiliary knowledge graph model in multi-turn dialogue generation.

Multi-turn dialogue generation is an essential and challenging subtask of text generation in the question answering system. Existing methods focused on extracting latent topic-level relevance or utilizing relevant external background knowledge. However, they are prone to ignore the fact that relying too much on latent aspects will lose subjective key information. Furthermore, there is not so much relevant external knowledge that can be used for referencing or a graph that has complete entity links. Dependency tree is a special structure that can be extracted from sentences, it covers the explicit key information of sentences. Therefore, in this paper, we proposed the EAGS model, which combines the subjective pivotal information from the explicit dependency tree with sentence implicit semantic information. The EAGS model is a knowledge graph enabled multi-turn dialogue generation model, and it doesn’t need extra external knowledge, it can not only extract and build a dependency knowledge graph from existing sentences, but also prompt the node representation, which is shared with Bi-GRU each time step word embedding in node semantic level. We store the specific domain subgraphs built by the EAGS, which can be retrieved as external knowledge graph in the future multi-turn dialogue generation task. We design a multi-task training approach to enhance semantics and structure local feature extraction, and balance with the global features. Finally, we conduct experiments on Ubuntu large-scale English multi-turn dialogue community dataset and English Daily dialogue dataset. Experiment results show that our EAGS model performs well on both automatic evaluation and human evaluation compared with the existing baseline models.

Full-text chemical identification with improved generalizability and tagging consistency.

Chemical identification involves finding chemical entities in text (i.e. named entity recognition) and assigning unique identifiers to the entities (i.e. named entity normalization). While current models are developed and evaluated based on article titles and abstracts, their effectiveness has not been thoroughly verified in full text. In this paper, we identify two limitations of models in tagging full-text articles: (1) low generalizability to unseen mentions and (2) tagging inconsistency. We use simple training and post-processing methods to address the limitations such as transfer learning and mention-wise majority voting. We also present a hybrid model for the normalization task that utilizes the high recall of a neural model while maintaining the high precision of a dictionary model. In the BioCreative VII NLM-Chem track challenge, our best model achieves 86.72 and 78.31 F1 scores in named entity recognition and normalization, significantly outperforming the median (83.73 and 77.49 F1 scores) and taking first place in named entity recognition. In a post-challenge evaluation, we re-implement our model and obtain 84.70 F1 score in the normalization task, outperforming the best score in the challenge by 3.34 F1 score. Database URL: https://github.com/dmis-lab/bc7-chem-id

Survey on English Entity Linking on Wikidata: Datasets and approaches

Wikidata is a frequently updated, community-driven, and multilingual knowledge graph. Hence, Wikidata is an attractive basis for Entity Linking, which is evident by the recent increase in published papers. This survey focuses on four subjects: (1) Which Wikidata Entity Linking datasets exist, how widely used are they and how are they constructed? (2) Do the characteristics of Wikidata matter for the design of Entity Linking datasets and if so, how? (3) How do current Entity Linking approaches exploit the specific characteristics of Wikidata? (4) Which Wikidata characteristics are unexploited by existing Entity Linking approaches? This survey reveals that current Wikidata-specific Entity Linking datasets do not differ in their annotation scheme from schemes for other knowledge graphs like DBpedia. Thus, the potential for multilingual and time-dependent datasets, naturally suited for Wikidata, is not lifted. Furthermore, we show that most Entity Linking approaches use Wikidata in the same way as any other knowledge graph missing the chance to leverage Wikidata-specific characteristics to increase quality. Almost all approaches employ specific properties like labels and sometimes descriptions but ignore characteristics such as the hyper-relational structure. Hence, there is still room for improvement, for example, by including hyper-relational graph embeddings or type information. Many approaches also include information from Wikipedia, which is easily combinable with Wikidata and provides valuable textual information, which Wikidata lacks.

Knowledge Fusion Analysis and Research Based on Knowledge Graph

With the rapid popularization of Internet technology, it is a new challenge to mine the hidden knowledge behind the data in an organized and directed way. Knowledge graph not only describes the content of semantic associations and entities existing in the objective world, but also uses graph structure to visually present the structured knowledge system for system users. Therefore, in the development of modern technology, knowledge graph has been widely concerned by industry and academia. In the era of big data, in order to build high-quality knowledge graph, knowledge fusion is very critical, among which entity alignment and entity link are important parts of knowledge fusion task. Starting from the field of film and television, this paper uses the entity alignment technology of NovEA model and the candidate entity ranking structure based on CNN-DSSM to deeply discuss the key technologies of knowledge fusion during the construction of multi-level film and television knowledge graph. The final experimental results prove that, compared with other models of the same task, the NovEA model studied in this paper has higher alignment accuracy, and the candidate entity ranking structure based on CNN-DSSM is better designed.

Knowledge Fusion Analysis and Research Based on Knowledge Graph

With the rapid popularization of Internet technology, it is a new challenge to mine the hidden knowledge behind the data in an organized and directed way. Knowledge graph not only describes the content of semantic associations and entities existing in the objective world, but also uses graph structure to visually present the structured knowledge system for system users. Therefore, in the development of modern technology, knowledge graph has been widely concerned by industry and academia. In the era of big data, in order to build high-quality knowledge graph, knowledge fusion is very critical, among which entity alignment and entity link are important parts of knowledge fusion task. Starting from the field of film and television, this paper uses the entity alignment technology of NovEA model and the candidate entity ranking structure based on CNN-DSSM to deeply discuss the key technologies of knowledge fusion during the construction of multi-level film and television knowledge graph. The final experimental results prove that, compared with other models of the same task, the NovEA model studied in this paper has higher alignment accuracy, and the candidate entity ranking structure based on CNN-DSSM is better designed.

BERN2: an advanced neural biomedical named entity recognition and normalization tool.

In biomedical natural language processing, named entity recognition (NER) and named entity normalization (NEN) are key tasks that enable the automatic extraction of biomedical entities (e.g. diseases and drugs) from the ever-growing biomedical literature. In this article, we present BERN2 (Advanced Biomedical Entity Recognition and Normalization), a tool that improves the previous neural network-based NER tool by employing a multi-task NER model and neural network-based NEN models to achieve much faster and more accurate inference. We hope that our tool can help annotate large-scale biomedical texts for various tasks such as biomedical knowledge graph construction.Availability and implementationWeb service of BERN2 is publicly available at http://bern2.korea.ac.kr. We also provide local installation of BERN2 at https://github.com/dmis-lab/BERN2.Supplementary information Supplementary data are available at Bioinformatics online.

Enhancing Botanical Knowledge Graphs with Machine Learning

Integrating sparse and incomplete biodiversity data into a global, coherent data space and generating machine-readable data infrastructures is a challenge in biodiversity informatics. In recent years, biodiversity data researchers have started proposing Knowledge Graphs (KGs) as one approach to connecting biodiversity data worldwide (Page 2019), representing the connections between the what, when, and where of objects in natural history collections. At the Natural History Museum (NHM) we have constructed a KG of botanical specimens and collectors, encoded into numerical representations, and using a Relational Graph Convolutional Network (RGCN) (Schlichtkrull et al. 2018) to infer gaps in the KG, forging new connections between nodes. The datasets involved in our botanical KG project are NHM Botany Collector database (105,780 entities) and NHM Indian Region Botanical Specimen Dataset (110,043 entities with geographical information). Our KG with RGCN enables the structured and contextual data to be reasoned across the knowledge content, allowing us to dynamically update its representation according to its closely related neighbours. Our work will explain why and how the KG with RGCN can offer a better way to link digitised botanical data. We use the prototype KG to demonstrate its potential for modelling botanical data and provide a graphical representation for other machine learning applications. For example, the combination of KG with RGCN and Metric Learning (Xing et al. 2002, a form of Machine Learning generally used to automatically construct task-specific distance metrics) supports data completion via entity classification and link prediction for a subset of botanical specimens within a geographic region. These data augmentation models with KGs allow us to identify gaps in specimen provenance, and fill in missing data. After phase one training, our model can achieve 88% accuracy in entity classification and report a reasonable Mean Reciprocal Rank (MRR) in raw ranking link prediction for the Indian Region Botanical Specimen Dataset. Our research also evaluates the use of the KG and RGCN to improve post-OCR (Optical Character Recognition) correction algorithms as part of automatic specimen digitisation pipelines. This improves the accuracy of entity recognition on specimen label text identification and transcription, as part of machine learning natural language processing and human-in-the-loop transcription. Human-based transcription can be aided and improved by an interpretation recommendation system predicated on the specimen unit’s RGCN-inferred location in the KG. This methodology can also be used to explore the alignment of KGs from different institutions within the global biodiversity network, to identify the relative importance of collectors or determine strengths or gaps in different geographic regions or ecosystems, duplicate items in collections, or objects in collections that have potentially been misidentified.

Research of Vertical Domain Entity Linking Method Fusing Bert-Binary

To solve the problem of unclear entity boundaries and low recognition accuracy in Chinese text, we construct the crop dataset and propose a Bert-binary-based entity link method. Candidate entity sets are generated through entity matching in multiple data sources. The Bert-binary model is called to calculate the correct probability of the candidate entity, and the entity with the highest score is screened for linking. In comparative experiments with three models on the crop dataset, the F 1 value is increased by 2.5% on the best method or by 8.8% on average. The experimental results show the effectiveness of Bert-binary method in this paper.

Computationally Efficient Context-Free Named Entity Disambiguation with Wikipedia

The induction of the semantics of unstructured text corpora is a crucial task for modern natural language processing and artificial intelligence applications. The Named Entity Disambiguation task comprises the extraction of Named Entities and their linking to an appropriate representation from a concept ontology based on the available information. This work introduces novel methodologies, leveraging domain knowledge extraction from Wikipedia in a simple yet highly effective approach. In addition, we introduce a fuzzy logic model with a strong focus on computational efficiency. We also present a new measure, decisive in both methods for the entity linking selection and the quantification of the confidence of the produced entity links, namely the relative commonness measure. The experimental results of our approach on established datasets revealed state-of-the-art accuracy and run-time performance in the domain of fast, context-free Wikification, by relying on an offline pre-processing stage on the corpus of Wikipedia. The methods introduced can be leveraged as stand-alone NED methodologies, propitious for applications on mobile devices, or in the context of vastly reducing the complexity of deep neural network approaches as a first context-free layer.

NILINKER: Attention-based approach to NIL Entity Linking

The existence of unlinkable (NIL) entities is a major hurdle affecting the performance of Named Entity Linking approaches, and, consequently, the performance of downstream models that depend on them. Existing approaches to deal with NIL entities focus mainly on clustering and prediction and are limited to general entities. However, other domains, such as the biomedical sciences, are also prone to the existence of NIL entities, given the growing nature of scientific literature. We propose NILINKER, a model that includes a candidate retrieval module for biomedical NIL entities and a neural network that leverages the attention mechanism to find the top-k relevant concepts from target Knowledge Bases (MEDIC, CTD-Chemicals, ChEBI, HP, CTD-Anatomy and Gene Ontology-Biological Process) that may partially represent a given NIL entity. We also make available a new evaluation dataset designated by EvaNIL, suitable for training and evaluating models focusing on the NIL entity linking task. This dataset contains 846,165 documents (abstracts and full-text biomedical articles), including 1,071,776 annotations, distributed by six different partitions: EvaNIL-MEDIC, EvaNIL-CTD-Chemicals, EvaNIL-ChEBI, EvaNIL-HP, EvaNIL-CTD-Anatomy and EvaNIL-Gene Ontology-Biological Process. NILINKER was integrated into a graph-based Named Entity Linking model (REEL) and the results of the experiments show that this approach is able to increase the performance of the Named Entity Linking model.