Name Disambiguation Research Articles

PubMed Computed Authors in 2024: an open resource of disambiguated author names in biomedical literature

Abstract Summary Over 55% of author names in PubMed are ambiguous: the same name is shared by different individual researchers. This poses significant challenges on precise literature retrieval for author name queries, a common behavior in biomedical literature search. In response, we present a comprehensive dataset of disambiguated authors. Specifically, we complement the automatic PubMed Computed Authors algorithm with the latest ORCID data for improved accuracy. As a result, the enhanced algorithm achieves high performance in author name disambiguation, and subsequently our dataset contains more than 21 million disambiguated authors for over 35 million PubMed articles and is incrementally updated on a weekly basis. More importantly, we make the dataset publicly available for the community such that it can be utilized in a wide variety of potential applications beyond assisting PubMed's author name queries. Finally, we propose a set of guidelines for best practices of authors pertaining to use of their names. Availability and Implementation The PubMed Computed Authors dataset is publicly available for bulk download at: https://ftp.ncbi.nlm.nih.gov/pub/lu/ComputedAuthors/. Additionally, it is available for query through web API at: https://www.ncbi.nlm.nih.gov/research/bionlp/APIs/authors/ Supplementary information Supplementary data are available at Bioinformatics online.

Towards Effective Author Name Disambiguation by Hybrid Attention

Towards Effective Author Name Disambiguation by Hybrid Attention

Bridging the gap in author names: building an enhanced author name dataset for biomedical literature system.

Author name incompleteness, referring to only first initial available instead of full first name, is a long-standing problem in MEDLINE and has a negative impact on biomedical literature systems. The purpose of this study is to create an Enhanced Author Names (EAN) dataset for MEDLINE that maximizes the number of complete author names. The EAN dataset is built based on a large-scale name comparison and restoration with author names collected from multiple literature databases such as MEDLINE, Microsoft Academic Graph, and Semantic Scholar. We assess the impact of EAN on biomedical literature systems by conducting comparative and statistical analyses between EAN and MEDLINE's author names dataset (MAN) on 2 important tasks, author name search and author name disambiguation. Evaluation results show that EAN improves the number of full author names in MEDLINE from 69.73 million to 110.9 million. EAN not only restores a substantial number of abbreviated names prior to the year 2002 when the NLM changed its author name indexing policy but also improves the availability of full author names in articles published afterward. The evaluation of the author name search and author name disambiguation tasks reveal that EAN is able to significantly enhance both tasks compared to MAN. The extensive coverage of full names in EAN suggests that the name incompleteness issue can be largely mitigated. This has significant implications for the development of an improved biomedical literature system. EAN is available at https://zenodo.org/record/10251358, and an updated version is available at https://zenodo.org/records/10663234.

High‐degree penalty based global statistical network embedding for name disambiguation in anonymized graph

SummaryIn person‐centric applications, the prevalence of shared names significantly hampers document retrieval, web search, and database integration, highlighting the critical need for name disambiguation. Network embedding based unsupervised name disambiguation methods have received much attention due to their wide applicability and superior disambiguation performance. However, existing methods require complex feature engineering, such as extracting biographical and source content features or constructing supplementary features from external knowledge bases, which are unavailable in privacy‐preserving scenarios. Moreover, they may face challenges such as imbalanced node training or overlooking global statistical information during node embedding learning. In this article, we propose a method to tackle the name disambiguation problem based on high‐degree penalty and global statistical information using only relational data. First, we construct a weighted source similarity network based on multi‐hop collaborator relationships. Second, we employ a high‐degree penalty based global statistical network embedding model to learn low‐dimensional node embeddings and preserve the structural features of the network. Finally, we cluster the same sources using a joint clustering algorithm that does not require prior knowledge of the number of clusters. The experiment validates the effectiveness of the proposed method on two real‐life datasets.

The National Institutes of Health Lasker Clinical Research Scholars Program: A Decade of Launching Clinician-Scientist Careers.

In response to the decades-long decrease in U.S. clinician-scientists, the National Institutes of Health (NIH) and the Albert and Mary Lasker Foundation launched the Lasker Clinical Research Scholars Program in academic year 2011 to 2012. The investigators examined the early outcomes of this program. Thirty-nine scholars have matriculated into the program as of May 2023. Productivity was assessed for all scholars who joined the program before October 2020 (n = 31). Extramural early-stage investigators (ESIs) were used as a control group, and coarsened exact matching was used to compare the groups. The scholars were compared with the matched ESIs on 4 productivity metrics: publication count, weighted relative citation ratio, clinical impact, and approximate potential to translate. Publication records for both groups were compiled using the NIH Office of Portfolio Analysis' name disambiguation method and manually curated to ensure integrity of the data set. Of the 39 scholars, 29 were compared with 121 matched extramural ESIs. Five years before matriculation, the 2 groups had comparable numbers of publications, but scholars had a higher median weighted relative citation ratio, clinical impact, and approximate potential to translate score. Five years after matriculation, the scholars had a higher median number of publications than the ESIs, and the gap between scholars and ESIs, with scholars having higher scores, had widened for all metrics except approximate potential to translate scores. Of 10 of the 39 scholars at or approaching tenure eligibility, 6 have attained tenure (3 at NIH and 3 in academic institutions), and 4 are on track to attain tenure at NIH. All the Lasker clinical research scholars are substantially involved in clinical and translational research. Their productivity matches or exceeds that of a matched cohort of ESIs at U.S. academic institutions.

Perspective of Digital Humanities on Person Names in Chinese Pre-Qin Classic

Knowledge annotation and mining from ancient Chinese classics have become a new trend in digital humanities research in China, and historical persons get the most attention. However, few studies have focused exclusively on person names, which is rather important for understanding Chinese traditional culture. This study focused on person names in Chinese Pre-Qin classics. We conducted a humanities computing study on Pre-Qin person name knowledge through an in-depth categorization and manual annotation of person name components. The results included the disambiguation of person names, a statistical distribution of famous persons, patterns in name components, and statistical analysis of name components. Furthermore, machine learning methods on the NER of person name knowledge were also examined, indicating the feasibility of future related research.

Name Disambiguation Scheme Based on Heterogeneous Academic Sites

Academic researchers publish their work in various formats, such as papers, patents, and research reports, on different academic sites. When searching for a particular researcher’s work, it can be challenging to pinpoint the right individual, especially when there are multiple researchers with the same name. In order to handle this issue, we propose a name disambiguation scheme for researchers with the same name based on heterogeneous academic sites. The proposed scheme collects and integrates research results from these varied academic sites, focusing on attributes crucial for disambiguation. It then employs clustering techniques to identify individuals who share the same name. Additionally, we implement the proposed rule-based algorithm name disambiguation method and the existing deep learning-based identification method. This approach allows for the selection of the most accurate disambiguation scheme, taking into account the metadata available in the academic sites, using a multi-classifier approach. We consider various researchers’ achievements and metadata of articles registered in various academic search sites. The proposed scheme showed an exceptionally high F1-measure value of 0.99. In this paper, we propose a multi-classifier that executes the most appropriate disambiguation scheme depending on the inputted metadata. The proposed multi-classifier shows the high F1-measure value of 0.67.

Disambiguation of company names via deep recurrent networks

Name Entity Disambiguation is the Natural Language Processing task of identifying textual records corresponding to the same Named Entity, i.e., real-world entities represented as a list of attributes (names, places, organisations, etc.). In this work, we face the task of disambiguating companies on the basis of their written names. We propose a Siamese LSTM Network approach to extract – via supervised learning – an embedding of company name strings in a (relatively) low dimensional vector space and use this representation to identify pairs of company names that actually represent the same company (i.e., the same Entity).Given that the manual labelling of string pairs is a rather onerous task, we analyse how an Active Learning approach to prioritise the samples to be labelled leads to a more efficient overall learning pipeline.The contributions of this work are: with empirical investigations on real-world industrial data, we show that our proposed Siamese Network outperforms several benchmark approaches based on standard string matching algorithms when enough labelled data are available; moreover, we show that Active Learning prioritisation is indeed helpful when labelling resources are limited, and let the learning models reach the out-of-sample performance saturation with less labelled data with respect to standard (random) data labelling approaches.

Automatic author name disambiguation by differentiable feature selection

Author name disambiguation (AND) is the task of resolving the ambiguity problem in bibliographic databases, where distinct real-world authors may share the same name or same author may have distinct names. The aim of AND is to split the name-ambiguous entities (articles) into the corresponding authors. Existing AND algorithms mainly focus on designing different similarity metrics between two ambiguous articles. However, most previous methods empirically select and process the features of entities, then use features to predict the similarity by data-driven models. In this article, we are motivated by natural questions: Which features are most useful for splitting name-ambiguous entities? Can they be automatically determined by an optimisation approach rather than heuristic feature engineering? Therefore, we proposed a novel end-to-end differentiable feature selection algorithm, automatically searching the optimal features for AND task (AAND). AAND optimises the discrete feature selection by differentiable Gumbel-Softmax, leading to the joint learning of feature selection policy and similarity prediction model. The experiments are conducted on a benchmark data set, S2AND, which harmonises eight different AND data sets. The results show that the performance of our proposal is superior to the advanced AND methods and feature selection algorithms. Meanwhile, deep insights into AND features are also given.

Graph-based methods for Author Name Disambiguation: a survey.

Scholarly knowledge graphs (SKG) are knowledge graphs representing research-related information, powering discovery and statistics about research impact and trends. Author name disambiguation (AND) is required to produce high-quality SKGs, as a disambiguated set of authors is fundamental to ensure a coherent view of researchers' activity. Various issues, such as homonymy, scarcity of contextual information, and cardinality of the SKG, make simple name string matching insufficient or computationally complex. Many AND deep learning methods have been developed, and interesting surveys exist in the literature, comparing the approaches in terms of techniques, complexity, performance, etc. However, none of them specifically addresses AND methods in the context of SKGs, where the entity-relationship structure can be exploited. In this paper, we discuss recent graph-based methods for AND, define a framework through which such methods can be confronted, and catalog the most popular datasets and benchmarks used to test such methods. Finally, we outline possible directions for future work on this topic.

Australian National Species List: name identifier management and linkages

The Australian National Species List (AuNSL) is the provider of names and taxonomy for significant national biodiversity data infrastructures including the Atlas of Living Australia, the Terrestrial Ecosystem Research Network, the Biodiversity Data Repository, and the Species Profile and Threats Database. The AuNSL mints persistent identifiers for names covered by the codes of nomenclature and name-like objects such as phrase names. To ensure sustainability of identifiers, a mapping service is provided to always resolve all AuNSL identifiers including historical and deprecated forms. Names are used as the building blocks for recording taxon name usages and taxon concepts. We provide services for matching, disambiguation and taxonomic resolution of names. The AuNSL does not exist in a vacuum and supports identifier mappings to external resources and related systems such as the International Plant Name Index (IPNI), Zoobank, the Biodiversity Heritage Library. To enable this integration, persistent identifiers from original and/or significant sources are required and this data is currently limited and incomplete within the AuNSL. To address this issue, we need to look backwards for improved ways of matching to existing persistent identifiers and forward to improving capture of taxonomic novelties and name-like objects and their identifiers.

Author Name Disambiguation Based on Heterogeneous Graph

<p>Since multiple people share the same name in the real world, this will cause performance degradation to academic search systems and lead to misattribution of publications. The author name disambiguation algorithm has not yet to be well solved. In this paper, we propose a disambiguation method that combines heterogeneous graph-based and improved label propagation, first we construct a publication heterogeneous graph network, then graph neural networks is applied to aggregate the nodes representation and relation types, finally combined with the improved label propagation algorithm to realize clustering. The task of author name disambiguation is completed to improve the retrieval performance. Experimental results on two public datasets show that our method was improved by 2.8% and 4.9% over the suboptimal method, respectively. Our method can effectively reduce the number of publications returning the wrong author and improve the performance of the academic retrieval system.</p> <p> </p>

A novel text representation which enables image classifiers to also simultaneously classify text, applied to name disambiguation

We introduce a novel method for converting text data into abstract image representations, which allows image-based processing techniques (e.g. image classification networks) to be applied to text-based comparison problems. We apply the technique to entity disambiguation of inventor names in US patents, obtaining a list of IDs which identify individual inventors with high accuracy. The method involves converting text from each pairwise comparison between two inventor name records into a 2D RGB (stacked) image representation. We then train an image classification neural network to discriminate between such pairwise comparison images. The trained neural network then labels each pair of records as either matched (same inventor) or non-matched (different inventors), producing highly accurate results. Our new text-to-image representation method could also be used more broadly for other text comparison problems, such as entity disambiguation of academic publications, or for problems that require simultaneous classification of both text and image datasets.

Deep author name disambiguation using DBLP data

In the academic world, the number of scientists grows every year and so does the number of authors sharing the same names. Consequently, it is challenging to assign newly published papers to their respective authors. Therefore, author name ambiguity is considered a critical open problem in digital libraries. This paper proposes an author name disambiguation approach that links author names to their real-world entities by leveraging their co-authors and domain of research. To this end, we use data collected from the DBLP repository that contains more than 5 million bibliographic records authored by around 2.6 million co-authors. Our approach first groups authors who share the same last names and same first name initials. The author within each group is identified by capturing the relation with his/her co-authors and area of research, represented by the titles of the validated publications of the corresponding author. To this end, we train a neural network model that learns from the representations of the co-authors and titles. We validated the effectiveness of our approach by conducting extensive experiments on a large dataset.

CluEval: A Python tool for evaluating clustering performance in named entity disambiguation

CluEval is a Python tool designed to assess the accuracy of named entity disambiguation methods in clustering performance. It allows users to employ five commonly used clustering evaluation metrics in entity disambiguation research. With newly developed, comprehensive, and fast algorithms, CluEval can handle large-scale computations and help users better understand and systematically interpret the clustering performance of named entity disambiguation methods. This tool can serve as a stand-alone evaluation code or be integrated as a module into any named entity disambiguation framework that produces clusters as the final disambiguation outputs, such as author name disambiguation.

PubExN: An Automated PubMed Bulk Article Extractor with Affiliation Normalization Package.

Biomedical article extraction is the preliminary step for every biomedical application. These applications are helpful in finding the gene, disease, chemical, drugs, protein entities. Finding entities relation such as gene-gene entities, drug-disease interaction, and chemical protein relation the PubExN can be helpful for these types of biomedical applications. In most cases, domain experts do this extraction process on their own. Human interference makes this process time-consuming and there is a high probability, that documents can be missed during the extraction process. To get rid of these complicated processes a python package is introduced to automate the process of bulk extraction from the PubMed database. The extraction process covers all the citation information with the associated abstract. The batch approach is used to extract the bulk extraction. The motivation for the development of PubExN was to provide flexibility for the extraction process of biomedical article's text data from NCBI's PubMed database. Basically, NCBI's PubMed database article contains the article id or can say PubMed-id (PMID), the title of the article, abstract, authors information, etc. This package will benefit many biomedical texts mining research including biomedical named entity recognition, biomedical relation extraction, literature discovery, knowledgebase creation, and various biomedical Natural Language Processing (NLP) tasks. In addition, it could be used in the author name disambiguation problems and new drug discoveries. This package will help save time and extra effort for the extraction and normalization process of PubMed articles.

Deep Author Name Disambiguation using DBLP Data

Deep Author Name Disambiguation using DBLP Data

Peculiarities of gender disambiguation and ordering of non-English authors’ names for Economic papers beyond core databases①

Abstract Purpose To supplement the quantitative portrait of Ukrainian Economics discipline with the results of gender and author ordering analysis at the level of individual authors, special methods of working with bibliographic data with a predominant share of non-English authors are used. The properties of gender mixing, the likelihood of male and female authors occupying the first position in the authorship list, as well as the arrangements of names are studied. Design/methodology/approach A data set containing bibliographic records related to Ukrainian journal publications in the field of Economics is constructed using Crossref metadata. Partial semi-automatic disambiguation of authors’ names is performed. First names, along with gender-specific ethnic surnames, are used for gender disambiguation required for further comparative gender analysis. Random reshuffling of data is used to determine the impact of gender correlations. To assess the level of alphabetization for our data set, both Latin and Cyrillic versions of names are taken into account. Findings The lack of well-structured metadata and the poor use of digital identifiers lead to numerous problems with automatization of bibliographic data pre-processing, especially in the case of publications by non-Western authors. The described stages for working with such specific data help to work at the level of authors and analyse, in particular, gender issues. Despite the larger number of female authors, gender equality is more likely to be reported at the individual level for the discipline of Ukrainian Economics. The tendencies towards collaborative or solo-publications and gender mixing patterns are found to be dependent on the journal: the differences for publications indexed in Scopus and/or Web of Science databases are found. It has also been found that Ukrainian Economics research is characterized by rather a non-alphabetical order of authors. Research limitations Only partial authors’ name disambiguation is performed in a semi-automatic way. Gender labels can be derived only for authors declared by full First names or gender-specific Last names. Practical implications The typical features of Ukrainian Economic discipline can be used to perform a comparison with other countries and disciplines, to develop an informed-based assessment procedure at the national level. The proposed way of processing publication data can be borrowed to enrich metadata about other research disciplines, especially for non-English speaking countries. Originality/value To our knowledge, this is the first large-scale quantitative study of Ukrainian Economic discipline. The results obtained are valuable not only at the national level, but also contribute to general knowledge about Economic research, gender issues, and authors’ names ordering. An example of the use of Crossref data is provided, while this data source is still less used due to a number of drawbacks. Here, for the first time, attention is drawn to the explicit use of the features of the Slavic authors’ names.

MORE: Toward Improving Author Name Disambiguation in Academic Knowledge Graphs

MORE: Toward Improving Author Name Disambiguation in Academic Knowledge Graphs

LAGOS‐AND: A large gold standard dataset for scholarly author name disambiguation

AbstractIn this article, we present a method to automatically build large labeled datasets for the author ambiguity problem in the academic world by leveraging the authoritative academic resources, ORCID and DOI. Using the method, we built LAGOS‐AND, two large, gold‐standard sub‐datasets for author name disambiguation (AND), of which LAGOS‐AND‐BLOCK is created for clustering‐based AND research and LAGOS‐AND‐PAIRWISE is created for classification‐based AND research. Our LAGOS‐AND datasets are substantially different from the existing ones. The initial versions of the datasets (v1.0, released in February 2021) include 7.5 M citations authored by 798 K unique authors (LAGOS‐AND‐BLOCK) and close to 1 M instances (LAGOS‐AND‐PAIRWISE). And both datasets show close similarities to the whole Microsoft Academic Graph (MAG) across validations of six facets. In building the datasets, we reveal the variation degrees of last names in three literature databases, PubMed, MAG, and Semantic Scholar, by comparing author names hosted to the authors' official last names shown on the ORCID pages. Furthermore, we evaluate several baseline disambiguation methods as well as the MAG's author IDs system on our datasets, and the evaluation helps identify several interesting findings. We hope the datasets and findings will bring new insights for future studies. The code and datasets are publicly available.