pith. machine review for the scientific record. sign in

arxiv: 2604.03776 · v1 · submitted 2026-04-04 · 💻 cs.DL · physics.soc-ph

Recognition: 2 theorem links

· Lean Theorem

Bridging the Language Gap in Scholarly Data I: Enhancing Author Disambiguation Algorithms for Chinese Names

Mingrong She , Liuhuaying Yang , Ana Maria Jaramillo , Lisette Esp\'in-Noboa
Authors on Pith no claims yet

Pith reviewed 2026-05-13 17:14 UTC · model grok-4.3

classification 💻 cs.DL physics.soc-ph
keywords author disambiguationChinese namesPinyinco-authorship networkscitation networksscientometricsrule-based methodscholarly data
0
0 comments X

The pith

A rule-based framework using networks and content similarity disambiguates Chinese names with F1 scores of 0.88 for Pinyin and 0.89 for characters.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents a method to distinguish different authors who share identical names, a frequent problem with Chinese names in global academic databases. Names written in Pinyin are especially hard to separate because many different characters map to the same romanized spelling. The approach combines co-authorship links, citation patterns, institutional affiliations, and text similarity into a set of rules. Tested on physics papers from a Chinese database covering more than 70 years, it outperforms simpler baselines on both Pinyin and original character versions of names. Reliable disambiguation matters because inaccurate authorship data undermines large studies of research productivity and influence.

Core claim

The paper claims that a rule-based disambiguation framework integrating co-authorship networks, citation networks, author affiliations, and content similarity resolves name ambiguity for Chinese scholars. Applied to 65,241 physics papers, the method reaches F1-scores of 0.88 on Pinyin names and 0.89 on character-based names in a human-annotated sample of 80 pairs, with gains driven by higher recall over two baseline methods. Performance remains comparable across writing systems, making the framework script-agnostic.

What carries the argument

The rule-based disambiguation framework that merges co-authorship and citation networks with affiliation and content similarity signals to cluster papers belonging to the same individual.

If this is right

  • Large-scale scientometric analyses can incorporate Chinese scholarly records without systematic undercounting of authors.
  • The same rules apply whether metadata supplies Pinyin or characters, reducing dependence on one script format.
  • Higher recall means more papers by the same person are correctly linked, improving measures of collaboration and impact.
  • The framework offers a practical starting point for processing other non-Latin name data in international repositories.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the rule set generalizes, similar pipelines could address name ambiguity in Korean, Arabic, or other romanized systems.
  • Applying the method to global citation databases might shift relative rankings of researchers from East Asia.
  • Adding lightweight machine learning on the same features could be tested as a direct extension to push recall even higher.
  • The 70-year span of the data allows tracking how name disambiguation needs change over time in one field.

Load-bearing premise

The 80 human-annotated name pairs sufficiently represent the ambiguities present across the full 65,241-paper dataset and that the selected network and content features alone can resolve most cases without further machine-learning steps.

What would settle it

Running the method on a fresh random sample of several hundred name pairs from the same dataset and finding that human reviewers disagree with the clusters often enough to drop average F1 below 0.80 would show the reported performance does not hold.

Figures

Figures reproduced from arXiv: 2604.03776 by Ana Maria Jaramillo, Lisette Esp\'in-Noboa, Liuhuaying Yang, Mingrong She.

Figure 1
Figure 1. Figure 1: Overview of the proposed rule-based framework for resolving author name ambiguity. A distinct name associated with multiple papers is considered ambiguous. To resolve this ambiguity, our framework evaluates co-authorship, affiliation, citation links, and content simi￾larity: if any criterion matches, the author names are merged as the same identity; otherwise, they are assigned to distinct identities. The … view at source ↗
Figure 2
Figure 2. Figure 2: Name disambiguation data-flow in Chinese and English datasets. The diagram presents the sequential filtering outcomes of the author name disambiguation algorithm applied separately to the Chinese dataset, where author names appear as Chinese characters (top panel), and the English translation dataset, where author names appear in Pinyin romanization (bottom panel). Each panel begins with all distinct names… view at source ↗
Figure 3
Figure 3. Figure 3: Cross-language disambiguation consistency. Distribution of average Jaccard similar￾ity between 106,411 Chinese identities and matching Pinyin identities (measuring overlap in assigned papers). The concentration at 1.0 (87.3%) indicates identical disambiguation across languages. 4.3 Evaluation We evaluate our algorithm against the human-annotated ground-truth dataset (see Section 3.3) using precision, recal… view at source ↗
Figure 4
Figure 4. Figure 4: Disambiguation performance comparison. Our method outperforms existing base￾lines (Sinatra et al. and Waqas & Qadir) across all metrics on both (a) Chinese and (b) English datasets, with particularly strong gains in recall. script representations fully avoid this error. The English dataset using Pinyin names achieves high but imperfect precision at 0.953 (Figure 4b), reflecting how romanization loses the d… view at source ↗
read the original abstract

Disambiguating scholars with identical names is essential for accurate authorship assignment and robust large-scale scientometric research. Existing methods are often designed for Latin-script metadata and perform poorly on Chinese names. In international publications, Chinese names typically appear as Romanized Pinyin, which is highly ambiguous as it can map to multiple distinct characters. Chinese characters, in contrast, reduce but do not eliminate this ambiguity, and are rarely available in international records. To address both challenges, we propose a rule-based disambiguation framework that integrates co-authorship networks, citation networks, author affiliations, and content similarity. We apply this framework to 65,241 physics papers from the China National Knowledge Infrastructure (CNKI), spanning over 70 years of data. On a human annotated sample of 80 name pairs, our method achieves F1-scores of 0.88 for Pinyin names and 0.89 for character-based names, outperforming two baseline approaches, with improvements driven primarily by higher recall. The comparable performance across both writing systems shows that our approach is script-agnostic, enabling reliable large-scale scientometric analyses.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript proposes a rule-based author disambiguation framework for Chinese names that integrates co-authorship networks, citation networks, author affiliations, and content similarity. It is applied to a corpus of 65,241 CNKI physics papers spanning over 70 years, with performance evaluated on a human-annotated sample of 80 name pairs yielding F1 scores of 0.88 for Pinyin names and 0.89 for character-based names, outperforming two unspecified baselines primarily via higher recall. The approach is presented as script-agnostic.

Significance. If the evaluation holds, the work would offer a transparent, parameter-free method for handling name ambiguity in Chinese scholarly data, a persistent gap in tools optimized for Latin scripts. The comparable results across Pinyin and character representations, combined with the rule-based design, could support more reliable large-scale scientometric studies on Chinese-language corpora.

major comments (2)
  1. [Evaluation] Evaluation section: The headline F1 scores (0.88 Pinyin, 0.89 character) and outperformance claim rest exclusively on a human-annotated sample of 80 name pairs. No sampling protocol (random, stratified, or otherwise), inter-annotator agreement, annotation guidelines, or statistical significance tests for the improvements are reported. This leaves open whether the sample captures the distribution of ambiguity cases in the full 65,241-paper corpus, including rare names, multi-author papers, and temporal variation over 70 years.
  2. [Methods] Methods section: The two baseline approaches are not described in sufficient detail (e.g., how they were implemented or adapted for Chinese names, any parameter settings, or feature usage). Without this information, the claim of outperformance cannot be independently verified or replicated.
minor comments (2)
  1. [Abstract] Abstract: The two baseline approaches are referenced but not named; specifying them (or at least their core ideas) would improve clarity for readers.
  2. [Discussion] The manuscript would benefit from a brief discussion of potential failure modes (e.g., cases where network features are sparse) to contextualize the reported recall gains.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments. We address each major comment below and will revise the manuscript to improve transparency and reproducibility.

read point-by-point responses

  1. Referee: [Evaluation] Evaluation section: The headline F1 scores (0.88 Pinyin, 0.89 character) and outperformance claim rest exclusively on a human-annotated sample of 80 name pairs. No sampling protocol (random, stratified, or otherwise), inter-annotator agreement, annotation guidelines, or statistical significance tests for the improvements are reported. This leaves open whether the sample captures the distribution of ambiguity cases in the full 65,241-paper corpus, including rare names, multi-author papers, and temporal variation over 70 years.

    Authors: We acknowledge that the current manuscript lacks explicit details on the annotation process. The 80 name pairs were chosen to represent a range of ambiguity scenarios drawn from the 65,241-paper corpus, including variations in name frequency, multi-author papers, and temporal coverage across the 70-year span. In the revised manuscript we will add a full description of the sampling protocol, annotation guidelines, inter-annotator agreement statistics, and statistical significance tests for the reported F1 improvements. These additions will clarify representativeness and strengthen the evaluation section. revision: yes

  2. Referee: [Methods] Methods section: The two baseline approaches are not described in sufficient detail (e.g., how they were implemented or adapted for Chinese names, any parameter settings, or feature usage). Without this information, the claim of outperformance cannot be independently verified or replicated.

    Authors: We agree that the baselines require more detailed description to support replication. In the revised manuscript we will expand the Methods section to fully specify the two baseline approaches, including their implementation, adaptations for Chinese names (both Pinyin and character forms), parameter settings, and feature usage. This will allow readers to verify the outperformance claims. revision: yes

Circularity Check

0 steps flagged

No circularity: rule-based method evaluated on external human labels

full rationale

The paper presents a rule-based disambiguation framework combining co-authorship networks, citation networks, affiliations, and content similarity. It reports F1 scores on a separate human-annotated sample of 80 name pairs drawn from the CNKI corpus. No equations, fitted parameters, or derivations are described that reduce to the inputs by construction. No self-citations are invoked as load-bearing uniqueness theorems or ansatzes. The evaluation uses independent external labels, satisfying the criterion for a self-contained result against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The framework rests on standard domain assumptions about network features being reliable author signals; no free parameters or new entities are introduced in the abstract.

axioms (1)
  • domain assumption Co-authorship, citation, affiliation, and content similarity features reliably indicate shared authorship for Chinese names
    Invoked as the basis for the rule-based integration without further justification in the abstract

pith-pipeline@v0.9.0 · 5515 in / 1272 out tokens · 30741 ms · 2026-05-13T17:14:51.010060+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

70 extracted references · 70 canonical work pages · 1 internal anchor

  1. [1]

    When different persons have an identical author name

    Dag W Aksnes. When different persons have an identical author name. how frequent are homonyms?Journal of the American Society for Information Science and Technology, 59(5):838–841, 2008

    work page 2008

  2. [2]

    Towards zero-shot cross-lingual named entity disambiguation.EXPERT SYSTEMS WITH APPLICATIONS, 184, DEC 1 2021

    Ander Barrena, Aitor Soroa, and Eneko Agirre. Towards zero-shot cross-lingual named entity disambiguation.EXPERT SYSTEMS WITH APPLICATIONS, 184, DEC 1 2021

    work page 2021

  3. [3]

    A robust web personal name information extraction system.EXPERT SYSTEMS WITH APPLICATIONS, 39(3):2690–2699, FEB 15 2012

    Ying Chen, Sophia Yat Mei Lee, and Chu-Ren Huang. A robust web personal name information extraction system.EXPERT SYSTEMS WITH APPLICATIONS, 39(3):2690–2699, FEB 15 2012

    work page 2012

  4. [4]

    Effective string processing and matching for author disambiguation.JOURNAL OF MACHINE LEARNING RESEARCH, 15:3037–3064, OCT 2014

    Wei-Sheng Chin, Yong Zhuang, Yu-Chin Juan, Felix Wu, Hsiao-Yu Tung, Tong Yu, Jui-Pin Wang, Cheng-Xia Chang, Chun-Pai Yang, Wei-Cheng Chang, Kuan-Hao Huang, Tzu-Ming Kuo, Shan-Wei Lin, Young-San Lin, Yu-Chen Lu, Yu-Chuan Su, Cheng-Kuang Wei, Tu-Chun Yin, Chun-Liang Li, Ting-Wei Lin, Cheng-Hao Tsai, Shou-De Lin, Hsuan-Tien Lin, and Chih- Jen Lin. Effective ...

    work page 2014

  5. [5]

    Enhancement of question answering system accuracy via transfer learning and bert.APPLIED SCIENCES- BASEL, 12(22), NOV 2022

    Kai Duan, Shiyu Du, Yiming Zhang, Yanru Lin, Hongzhuo Wu, and Quan Zhang. Enhancement of question answering system accuracy via transfer learning and bert.APPLIED SCIENCES- BASEL, 12(22), NOV 2022

    work page 2022

  6. [6]

    Chinese personal name disambiguation based on clustering.WIRELESS COMMUNICATIONS & MOBILE COMPUTING, 2021, MAY 15 2021

    Chao Fan and Yu Li. Chinese personal name disambiguation based on clustering.WIRELESS COMMUNICATIONS & MOBILE COMPUTING, 2021, MAY 15 2021

    work page 2021

  7. [7]

    A brief survey of automatic methods for author name disambiguation.Acm Sigmod Record, 41(2):15–26, 2012

    Anderson A Ferreira, Marcos Andr´ e Gon¸ calves, and Alberto HF Laender. A brief survey of automatic methods for author name disambiguation.Acm Sigmod Record, 41(2):15–26, 2012

    work page 2012

  8. [8]

    Research identifiers: Orcid, doi, and the issue with wang and smith

    Stuart I Granshaw. Research identifiers: Orcid, doi, and the issue with wang and smith. Photogrammetric Record, 34(167), 2019

    work page 2019

  9. [9]

    Some linguistic issues in the machine transliteration of chinese, japanese, and arabic names.ACL 2016, page 47, 2016

    Jack Halpern. Some linguistic issues in the machine transliteration of chinese, japanese, and arabic names.ACL 2016, page 47, 2016. 9

    work page 2016

  10. [10]

    Semantic fingerprints-based author name disambiguation in chinese documents.SCIENTOMETRICS, 111(3):1879–1896, JUN 2017

    Hongqi Han, Changqing Yao, Yuan Fu, Yongsheng Yu, Yunliang Zhang, and Shuo Xu. Semantic fingerprints-based author name disambiguation in chinese documents.SCIENTOMETRICS, 111(3):1879–1896, JUN 2017. 6th Global Tech Mining Conference, Valencia, SPAIN, SEP, 2016

    work page 2017

  11. [11]

    Health warning: might contain multiple personalities-the problem of homonyms in thomson reuters essential science indicators.SCIENTOMETRICS, 105(3):2259– 2270, DEC 2015

    Anne-Wil Harzing. Health warning: might contain multiple personalities-the problem of homonyms in thomson reuters essential science indicators.SCIENTOMETRICS, 105(3):2259– 2270, DEC 2015

    work page 2015

  12. [12]

    Health warning: might contain multiple personalities—the problem of homonyms in thomson reuters essential science indicators.Scientometrics, 105:2259–2270, 2015

    Anne-Wil Harzing. Health warning: might contain multiple personalities—the problem of homonyms in thomson reuters essential science indicators.Scientometrics, 105:2259–2270, 2015

    work page 2015

  13. [13]

    A novel approach for entity resolution in scientific documents using context graphs.INFORMATION SCIENCES, 432:431–441, MAR 2018

    Changqin Huang, Jia Zhu, Xiaodi Huang, Min Yang, Gabriel Fung, and Qintai Hu. A novel approach for entity resolution in scientific documents using context graphs.INFORMATION SCIENCES, 432:431–441, MAR 2018

    work page 2018

  14. [14]

    Institution information specification and correlation based on institutional pids and ind tool.SCIENTOMETRICS, 122(1):381–396, JAN 2020

    Yongwen Huang, Jiao Li, Tan Sun, and Guojian Xian. Institution information specification and correlation based on institutional pids and ind tool.SCIENTOMETRICS, 122(1):381–396, JAN 2020

    work page 2020

  15. [15]

    A chinese expert disambigua- tion method based on semi-supervised graph clustering.INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 6(2):197–204, APR 2015

    Jin Jiang, Xin Yan, Zhengtao Yu, Jianyi Guo, and Wei Tian. A chinese expert disambigua- tion method based on semi-supervised graph clustering.INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 6(2):197–204, APR 2015

    work page 2015

  16. [16]

    Chinese short text entity disambiguation based on the dual-channel hybrid network.IEEE ACCESS, 8:206164– 206173, 2020

    Liting Jiang, Gulila Altenbek, Di Wu, Yajing Ma, and Hayinaer Aierzhati. Chinese short text entity disambiguation based on the dual-channel hybrid network.IEEE ACCESS, 8:206164– 206173, 2020

    work page 2020

  17. [17]

    Jinseok Kim and Jana Diesner. Distortive effects of initial-based name disambiguation on measurements of large-scale coauthorship networks.Journal of the Association for Information Science and Technology, 67(6):1446–1461, 2016

    work page 2016

  18. [18]

    Effect of chinese characters on machine learning for chinese author name disambiguation: A counterfactual evaluation.Journal of Information Science, 49(3):711–725, 2023

    Jinseok Kim, Jenna Kim, and Jinmo Kim. Effect of chinese characters on machine learning for chinese author name disambiguation: A counterfactual evaluation.Journal of Information Science, 49(3):711–725, 2023

    work page 2023

  19. [19]

    Effect of chinese characters on machine learning for chinese author name disambiguation: A counterfactual evaluation.JOURNAL OF INFORMA- TION SCIENCE, 49(3):711–725, JUN 2023

    Jinseok Kim, Jenna Kim, and Jinmo Kim. Effect of chinese characters on machine learning for chinese author name disambiguation: A counterfactual evaluation.JOURNAL OF INFORMA- TION SCIENCE, 49(3):711–725, JUN 2023

    work page 2023

  20. [20]

    Researcher name resolver: Identifier management system for japanese researchers.International Journal on Digital Libraries, 14(1):39–58, 2014

    Kei Kurakawa, Hideaki Takeda, Masao Takaku, Akiko Aizawa, Ryo Shiozaki, Shun Morimoto, and Hideki Uchijima. Researcher name resolver: Identifier management system for japanese researchers.International Journal on Digital Libraries, 14(1):39–58, 2014

    work page 2014

  21. [21]

    Tsdw: Two-stage word sense disambigua- tion using wikipedia.JOURNAL OF THE AMERICAN SOCIETY FOR INFORMATION SCIENCE AND TECHNOLOGY, 64(6):1203–1223, JUN 2013

    Chenliang Li, Aixin Sun, and Anwitaman Datta. Tsdw: Two-stage word sense disambigua- tion using wikipedia.JOURNAL OF THE AMERICAN SOCIETY FOR INFORMATION SCIENCE AND TECHNOLOGY, 64(6):1203–1223, JUN 2013

    work page 2013

  22. [22]

    Context effects and the processing of spoken homophones.READING AND WRITING, 10(3-5):223–243, OCT 1998

    P Li and MC Yip. Context effects and the processing of spoken homophones.READING AND WRITING, 10(3-5):223–243, OCT 1998

    work page 1998

  23. [23]

    Japanese-chinese information retrieval with an iterative weighting scheme.JOURNAL OF INFORMATION SCIENCE AND ENGINEERING, 26(2):685–697, MAR 2010

    Chu-Cheng Lin, Yu-Chun Wang, and Richard Tzong-Han Tsai. Japanese-chinese information retrieval with an iterative weighting scheme.JOURNAL OF INFORMATION SCIENCE AND ENGINEERING, 26(2):685–697, MAR 2010. National Computer Symposium, Taichung, TAI- WAN, DEC, 2007

    work page 2010

  24. [24]

    A survey of crf algorithm based knowledge extrac- tion of elementary mathematics in chinese.MOBILE NETWORKS & APPLICATIONS, 26(5, SI):1891–1903, OCT 2021

    Shuai Liu, Tenghui He, and Jianhua Dai. A survey of crf algorithm based knowledge extrac- tion of elementary mathematics in chinese.MOBILE NETWORKS & APPLICATIONS, 26(5, SI):1891–1903, OCT 2021

    work page 1903

  25. [25]

    McFarland, 2008

    Emma Woo Louie.Chinese American names: Tradition and transition. McFarland, 2008

    work page 2008

  26. [26]

    A graph-based author name disambiguation method and analysis via information theory.ENTROPY, 22(4), APR 2020

    Yingying Ma, Youlong Wu, and Chengqiang Lu. A graph-based author name disambiguation method and analysis via information theory.ENTROPY, 22(4), APR 2020. 10

    work page 2020

  27. [27]

    Manzoor, S

    A. Manzoor, S. Asghar, and Tehmina Amjad. Toward a new paradigm for author name disam- biguation.IEEE Access, 10:76055–76068, 2022

    work page 2022

  28. [28]

    Mesh now: automatic mesh indexing at pubmed scale via learning to rank.JOURNAL OF BIOMEDICAL SEMANTICS, 8, APR 17 2017

    Yuqing Mao and Zhiyong Lu. Mesh now: automatic mesh indexing at pubmed scale via learning to rank.JOURNAL OF BIOMEDICAL SEMANTICS, 8, APR 17 2017

    work page 2017

  29. [29]

    Efficient Estimation of Word Representations in Vector Space

    Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient estimation of word representations in vector space.arXiv preprint arXiv:1301.3781, 2013

    work page internal anchor Pith review Pith/arXiv arXiv 2013

  30. [30]

    Named entity disambiguation based on classified and structural semantic relatedness.CHINESE JOURNAL OF ELEC- TRONICS, 27(6):1176–1182, NOV 2018

    Chai Mingke, Li Dongmei, Zhuang Tingting, and Yang Shuyi. Named entity disambiguation based on classified and structural semantic relatedness.CHINESE JOURNAL OF ELEC- TRONICS, 27(6):1176–1182, NOV 2018

    work page 2018

  31. [31]

    Understanding orcid adoption among academic researchers.Scientometrics, 130(5):2783–2797, 2025

    Stephen R Porter, Paul D Umbach, and Chris Willis. Understanding orcid adoption among academic researchers.Scientometrics, 130(5):2783–2797, 2025

    work page 2025

  32. [32]

    A note on the topic of single-author articles in science.Scientometrics, 130(5):3071– 3088, 2025

    Petr Praus. A note on the topic of single-author articles in science.Scientometrics, 130(5):3071– 3088, 2025

    work page 2025

  33. [33]

    Jane Qiu. Identity crisis: Chinese authors are publishing more and more papers, but are they receiving due credit and recognition for their work? not if their names get confused along the way.Nature, 451(7180):766–768, 2008

    work page 2008

  34. [34]

    Using monte carlo simulations to assess the impact of author name dis- ambiguation quality on different bibliometric analyses.Scientometrics, 107:1283 – 1298, 2016

    Jan-Frederic Schulz. Using monte carlo simulations to assess the impact of author name dis- ambiguation quality on different bibliometric analyses.Scientometrics, 107:1283 – 1298, 2016

    work page 2016

  35. [35]

    chinese- names.https://github.com/CSHVienna/chinese-names, 2026

    Mingrong She, Liuhuaying Yang, Ana Maria Jaramillo, and Lisette Esp´ ın-Noboa. chinese- names.https://github.com/CSHVienna/chinese-names, 2026. GitHub repository

    work page 2026

  36. [36]

    Quantifying the evolution of individual scientific impact.Science, 354(6312):aaf5239, 2016

    Roberta Sinatra, Dashun Wang, Pierre Deville, Chaoming Song, and Albert-L´ aszl´ o Barab´ asi. Quantifying the evolution of individual scientific impact.Science, 354(6312):aaf5239, 2016

    work page 2016

  37. [37]

    Author name disambiguation.Annual review of information science and technology, 43(1):1, 2009

    Neil R Smalheiser, Vetle I Torvik, et al. Author name disambiguation.Annual review of information science and technology, 43(1):1, 2009

    work page 2009

  38. [38]

    Transitioning to the next generation of metadata

    Karen Smith-Yoshimura. Transitioning to the next generation of metadata. oclc research report. OCLC Online Computer Library Center, Inc., 2020

    work page 2020

  39. [39]

    Deep convolutional neu- ral network based medical concept normalization.IEEE TRANSACTIONS ON BIG DATA, 8(5):1195–1208, OCT 1 2022

    Guojie Song, Qingqing Long, Yi Luo, Yiming Wang, and Yilun Jin. Deep convolutional neu- ral network based medical concept normalization.IEEE TRANSACTIONS ON BIG DATA, 8(5):1195–1208, OCT 1 2022

    work page 2022

  40. [40]

    Andreas Strotmann and Dangzhi Zhao. Author name disambiguation: What difference does it make in author-based citation analysis?JOURNAL OF THE AMERICAN SOCIETY FOR INFORMATION SCIENCE AND TECHNOLOGY, 63(9):1820–1833, SEP 2012

    work page 2012

  41. [41]

    Andreas Strotmann and Dangzhi Zhao. Author name disambiguation: What difference does it make in author-based citation analysis?Journal of the American Society for Information Science and Technology, 63(9):1820–1833, 2012

    work page 2012

  42. [42]

    Name disambiguation for chinese scientific authors with multi-level clustering

    Simeng Sun, Hui Zhang, Ning Li, and Yong Chen. Name disambiguation for chinese scientific authors with multi-level clustering. In2017 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiqui- tous Computing (EUC), volume 1, pages 176–182. IEEE, 2017

    work page 2017

  43. [43]

    Disambiguation of korean names in references.Journal of Information Science Theory and Practice, 6(2):62–70, 2018

    Kim Sungwon. Disambiguation of korean names in references.Journal of Information Science Theory and Practice, 6(2):62–70, 2018

    work page 2018

  44. [44]

    Jie Tang, A. C. M. Fong, Bo Wang, and Jing Zhang. A unified probabilistic framework for name disambiguation in digital library.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 24(6):975–987, JUN 2012

    work page 2012

  45. [45]

    A combination approach to web user profiling

    Jie Tang, Limin Yao, Duo Zhang, and Jing Zhang. A combination approach to web user profiling. ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 5(1), DEC 2010

    work page 2010

  46. [46]

    Chinese names in the biomedical literature: Suggested bibliometric standardization.Publishing Research Quarterly, 36(2):254–257, 2020

    Jaime A Teixeira da Silva. Chinese names in the biomedical literature: Suggested bibliometric standardization.Publishing Research Quarterly, 36(2):254–257, 2020. 11

    work page 2020

  47. [47]

    Tseng, and Wen- Lian Hsu

    Chen-Kai Wang, Feng-Duo Wang, You-Qian Lee, Pei-Tsz Chen, Bo-Hong Wang, Chu-Hsien Su, Joseph Chin-Chi Kuo, Chi-Shin Wu, Yi-Ling Chien, Hong-Jie Dai, Vincent S. Tseng, and Wen- Lian Hsu. Principle-based approach for the de-identification of code-mixed electronic health records.IEEE ACCESS, 10:22875–22885, 2022

    work page 2022

  48. [48]

    Longarms: Fraud pre- diction in online lending services using sparse knowledge graph.IEEE TRANSACTIONS ON BIG DATA, 9(2):758–772, APR 1 2023

    Cheng Wang, Hangyu Zhu, Ruixin Hu, Rui Li, and Changjun Jiang. Longarms: Fraud pre- diction in online lending services using sparse knowledge graph.IEEE TRANSACTIONS ON BIG DATA, 9(2):758–772, APR 1 2023

    work page 2023

  49. [49]

    Named entity disambiguation for questions in community question answering.KNOWLEDGE-BASED SYSTEMS, 126:68–77, JUN 15 2017

    Fang Wang, Wei Wu, Zhoujun Li, and Ming Zhou. Named entity disambiguation for questions in community question answering.KNOWLEDGE-BASED SYSTEMS, 126:68–77, JUN 15 2017

    work page 2017

  50. [50]

    Multilayer heuristics based clustering framework (MHCF) for author name disambiguation.Scientometrics, 126(9):7637–7678, 2021

    Humaira Waqas and Muhammad Abdul Qadir. Multilayer heuristics based clustering framework (MHCF) for author name disambiguation.Scientometrics, 126(9):7637–7678, 2021

    work page 2021

  51. [51]

    Author name disambiguation based on semi- supervised learning with graph convolutional network.JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 43(12):3442–3450, DEC 2021

    Sheng Xiaoguang, Wang Ying, and Qian Li. Author name disambiguation based on semi- supervised learning with graph convolutional network.JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 43(12):3442–3450, DEC 2021

    work page 2021

  52. [52]

    Rousseau, Xin Li, Weijia Xu, Vetle I

    Jian Xu, Sunkyu Kim, Min Song, Minbyul Jeong, Donghyeon Kim, Jaewoo Kang, Justin F. Rousseau, Xin Li, Weijia Xu, Vetle I. Torvik, Yi Bu, Chongyan Chen, Islam Akef Ebeid, Daifeng Li, and Ying Ding. Building a pubmed knowledge graph.SCIENTIFIC DATA, 7(1), JUN 26 2020

    work page 2020

  53. [53]

    Incorporating multi-kernel function and internet verification for chinese person name disambiguation.FRONTIERS OF COMPUTER SCIENCE, 10(6):1026–1038, DEC 2016

    Ruifeng Xu, Lin Gui, Qin Lu, Shuai Wang, and Jian Xu. Incorporating multi-kernel function and internet verification for chinese person name disambiguation.FRONTIERS OF COMPUTER SCIENCE, 10(6):1026–1038, DEC 2016

    work page 2016

  54. [54]

    Rethinking the author name ambiguity problem and beyond: The case of the chinese context.Accountability in Research, pages 1–24, 2024

    Shaoxiong Brian Xu and Guangwei Hu. Rethinking the author name ambiguity problem and beyond: The case of the chinese context.Accountability in Research, pages 1–24, 2024

    work page 2024

  55. [55]

    A topic models based framework for detecting and forecasting emerging technologies.TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE, 162, JAN 2021

    Shuo Xu, Liyuan Hao, Guancan Yang, Kun Lu, and Xin An. A topic models based framework for detecting and forecasting emerging technologies.TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE, 162, JAN 2021

    work page 2021

  56. [56]

    Large-scale name disambiguation of chinese patent inventors (1985-2016).SCIENTOMETRICS, 122(2):765–790, FEB 2020

    Deyun Yin, Kazuyuki Motohashi, and Jianwei Dang. Large-scale name disambiguation of chinese patent inventors (1985-2016).SCIENTOMETRICS, 122(2):765–790, FEB 2020

    work page 1985

  57. [57]

    Porter, and Philip Shapira

    Jan Youtie, Stephen Carley, Alan L. Porter, and Philip Shapira. Tracking researchers and their outputs: new insights from orcids.SCIENTOMETRICS, 113(1):437–453, OCT 2017

    work page 2017

  58. [58]

    Who are the international research collaboration partners for china? a novel data perspective based on nsfc grants.Scientometrics, 116:401–422, 2018

    Lili Yuan, Yanni Hao, Minglu Li, Chunbing Bao, Jianping Li, and Dengsheng Wu. Who are the international research collaboration partners for china? a novel data perspective based on nsfc grants.Scientometrics, 116:401–422, 2018

    work page 2018

  59. [59]

    Multilingual closed caption translation sys- tem for digital television.IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, E89D(6):1885–1892, JUN 2006

    Sanghwa Yuh, Kongjoo Lee, and Jungyun Seo. Multilingual closed caption translation sys- tem for digital television.IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, E89D(6):1885–1892, JUN 2006

    work page 2006

  60. [60]

    A normalized levenshtein distance metric.IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(6):1091–1095, 2007

    Li Yujian and Liu Bo. A normalized levenshtein distance metric.IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(6):1091–1095, 2007

    work page 2007

  61. [61]

    Increasing trend of scientists to switch between topics.Nature communications, 10(1):3439, 2019

    An Zeng, Zhesi Shen, Jianlin Zhou, Ying Fan, Zengru Di, Yougui Wang, H Eugene Stanley, and Shlomo Havlin. Increasing trend of scientists to switch between topics.Nature communications, 10(1):3439, 2019

    work page 2019

  62. [62]

    Entity linking on chinese microblogs via deep neural network.IEEE ACCESS, 6:25908–25920, 2018

    Weixin Zeng, Jiuyang Tang, and Xiang Zhao. Entity linking on chinese microblogs via deep neural network.IEEE ACCESS, 6:25908–25920, 2018

    work page 2018

  63. [63]

    Neural network-based tree translation for knowledge base construction.IEEE ACCESS, 9:38706–38717, 2021

    Haijun Zhang. Neural network-based tree translation for knowledge base construction.IEEE ACCESS, 9:38706–38717, 2021

    work page 2021

  64. [64]

    Qin Zhang, Xuyu Xiang, Jiaohua Qin, Yun Tan, Qiang Liu, and Neal N. Xiong. Short text entity disambiguation algorithm based on multi-word vector ensemble.INTELLIGENT AU- TOMATION AND SOFT COMPUTING, 30(1):227–241, 2021. 12

    work page 2021

  65. [65]

    Entity linking method for chinese short text based on siamese-like network.INFORMATION, 13(8), AUG 2022

    Yang Zhang, Jin Liu, Bo Huang, and Bei Chen. Entity linking method for chinese short text based on siamese-like network.INFORMATION, 13(8), AUG 2022

    work page 2022

  66. [66]

    China’s emerging centrality in the contemporary international scientific collaboration network.Scientometrics, 116(2):1075–1091, 2018

    Zhihui Zhang, Jason E Rollins, and Evangelia Lipitakis. China’s emerging centrality in the contemporary international scientific collaboration network.Scientometrics, 116(2):1075–1091, 2018

    work page 2018

  67. [67]

    An in- vestigation of the relationship between scientists’ mobility to/from china and their research performance.JOURNAL OF INFORMETRICS, 14(2), MAY 2020

    Zhenyue Zhao, Yi Bu, Lele Kang, Chao Min, Yiyang Bian, Li Tang, and Jiang Li. An in- vestigation of the relationship between scientists’ mobility to/from china and their research performance.JOURNAL OF INFORMETRICS, 14(2), MAY 2020

    work page 2020

  68. [68]

    Dual-channel heterogeneous graph network for author name disambiguation.INFORMATION, 12(9), SEP 2021

    Xin Zheng, Pengyu Zhang, Yanjie Cui, Rong Du, and Yong Zhang. Dual-channel heterogeneous graph network for author name disambiguation.INFORMATION, 12(9), SEP 2021

    work page 2021

  69. [69]

    Self-supervised en- hancement for named entity disambiguation via multimodal graph convolution.IEEE TRANS- ACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022 MAY 13 2022

    Pengfei Zhou, Kaining Ying, Zhenhua Wang, Dongyan Guo, and Cong Bai. Self-supervised en- hancement for named entity disambiguation via multimodal graph convolution.IEEE TRANS- ACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022 MAY 13 2022

    work page 2022

  70. [70]

    match” or “not match

    Jia Zhu, Xingcheng Wu, Xueqin Lin, Changqin Huang, Gabriel Pui Cheong Fung, and Yong Tang. A novel multiple layers name disambiguation framework for digital libraries using dynamic clustering.SCIENTOMETRICS, 114(3):781–794, MAR 2018. 13 Supplementary Information S1 Systematic literature search To identify prior work on Chinese name disambiguation, we cond...

    work page 2018