=Paper=
{{Paper
|id=Vol-2543/rpaper03
|storemode=property
|title=Matching of Authors and Publications in Multilingual Bibliographic Knowledge Bases
|pdfUrl=https://ceur-ws.org/Vol-2543/rpaper03.pdf
|volume=Vol-2543
|authors=Zinaida Apanovich
|dblpUrl=https://dblp.org/rec/conf/ssi/Apanovich19
}}
==Matching of Authors and Publications in Multilingual Bibliographic Knowledge Bases==
https://ceur-ws.org/Vol-2543/rpaper03.pdf
Matching of Authors and Publications in Multilingual
Bibliographic Knowledge Bases
Zinaida Apanovich[0000-0002-5767-284X]
A.P. Ershov Institute of Informatics Systems SB RAS, 6, Acad. Lavrentjev pr.,
Novosibirsk 630090, Russia
Novosibirsk State University, 1, Pirogova str., Novosibirsk, 630090, Russia
apanovich@iis.nsk.su
Abstract. The cross-lingual matching of authors and publications is a special
case of the task of assigning a unique identifier to the same real-world entity in
multilingual data sources. This paper presents the results of experiments with
the several versions of a cross-lingual system designed to match, basing on a
Russian-language data source, the authors and English-language publications.
Since different heuristics have been tested in these versions of the system, we
consider here only those that have given the best results. An important element
of the system is its interactive visualization tool, which gives information on the
distribution of publications by authors, as well as providing the ability to edit
the results of the analysis. The visualization system is supplemented with meth-
ods for similarity matrices ordering. Experiments have shown that the main
source of improving the quality of the matching and clustering algorithm is ex-
tending the set of confirmed publications. The approaches used in this system
are applicable to solving the problem of linking named entities in various multi-
lingual data sources.
Keywords: Multilingual Knowledge Bases, Cross-Lingual Matching of Au-
thors and Publications, Entity Resolution, Clustering, Interactive Visualization.
1 Introduction
Nowadays, entity resolution is being intensively investigated in the context of the
integration of heterogeneous data sets. Collecting data from heterogeneous data sets
and integrating them in a query able environment increases completeness and correct-
ness as well as ensures a more effective analysis. Of special interest is the problem of
cross-lingual entity resolution for multilingual data integration since local language
data sources are often more complete and accurate than global data sources.
Although English is the main language for research and the Internet, a great num-
ber of research publications belong to non-English authors and are translated from
various foreign languages, which make the task of integrating multiple data sources
even more difficult. Naturally, this poses the problem of the cross-language disam-
biguation of named entities and, in particular, the cross-language matching of authors
and publications [1, 2].
Copyright © 2020 for this paper by its authors.
Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
27
Our previous research has demonstrated that Russian names allowing several trans-
literations represent a challenge for international data bases and knowledge graphs.
Experiments with several multilingual datasets have shown that Russian names admit-
ting several transliterations are often treated as homonyms, and several different per-
sons with identical name variations are treated as synonyms [3, 4]. This is especially
annoying when errors occur in the resources calculating scientific ratings, such as
Scopus and Web of Science.
For example, the papers by Виктор Карлович Сабельфельд are assigned in the
Scopus data base [5] to three people with distinct Scopus identifiers and distinct lists
of publications. Meanwhile, if we compare these data with the Russian site eLI-
BRARY.ru [6], we will realize that Victor K. Sabelfeld and V.K. Sabel’fel’d from the
A.P. Ershov Institute of Informatics Systems, as well as Viktor Sabelfeld from the
Karlsruhe Institute of Technology, are in fact the same person.
Thanks to the projects such as ORCID [7] and to the continual interaction of re-
searchers with the of Web of Science and Scopus developers [8], the quality of data
presented at these sites has improved. However, there is a great number of other
scholarly data sources, and it is impossible verify all of them manually. For example,
the Springer Nature SciGraph [9], a Linked Open Data platform, collecting infor-
mation about conferences, publications, affiliations, and research projects, has the
same problem with information on researchers having Russian names. There are two
persons, named Victor Sabelfeld and VK Sabel’Fel’D, with distinct identifiers and
distinct lists of papers. Besides, there are many papers authored by a real person,
Viktor Karlovich Sabelfeld, which are not assigned to anybody in the SN SciGraph.
Instead, the authors of such publications are represented by blank nodes and the prop-
erties of these blank nodes are described by means of several literal triples. For exam-
ple, the property shema:affiliation of the blank node https://scigraph.springernature.
com/pub.10.1007/3-540-08065-1_5#N54dbe9edfb2343559c2d95777627d496 is de-
scribed by another blank node having the type schema:Organization and the name
“Computing Center, Nowosibirsk, USSR,” the organization that ceased to exist about
thirty years ago. This example demonstrates another global problem of most interna-
tional data bases: data incompleteness with regard to Russian organizations. The SN
SciGraph uses the GRID data base [10] as the source of general information about
research organizations. GRID contains information on 2,033 Russian research organi-
zations while the Russian eLIBRARY.ru data set contains a list of more than 13,000
research organizations. For example, the GRID data base has no information about
the A.P. Ershov Institute of Informatics Systems. Consequently, the SN SciGraph has
no information on the affiliation of all the researchers of this institute, which creates
additional problems with the identification of the publications authors.
Since similar situations are quite common, our main objective is to investigate var-
ious methods to enrich and improve an English-language data source(s) by comparing
its (their) content with national data sources in local languages, such as the Russian-
language data sources.
An algorithm for the cross-language identity resolution using the SBRAS Open
Archive is presented in [3]. The algorithm relied heavily on the information about
Siberian researchers and their affiliations and for this reason had a very limited appli-
28
cation. A possible solution to this problem would be using a larger data source such as
eLIBRARY.ru.
To this end, a way of establishing correspondence between the Russian-named and
English-named entities has to be developed. The transliteration-based matching of
personal names was already described in [3]; our new algorithm, however, has an
additional matching step, enabling us to create groups of confirmed papers for an
individual researcher. Another issue is establishing the correspondence between the
titles of original Russian papers and their English translations as well as between
journal titles in Russian and their English translations. Due to this extended matching
step, the new clustering algorithm for matching authors and publications has proven
to be more efficient that the previous one. Finally, an interactive visualization algo-
rithm provides comprehensible matching and clustering results and enables their
analysis and modification. In particular, interactive visualization of similarity matrices
based on different similarity measures has shown that the main source of improving
the quality of the matching and clustering algorithm is extending the set of confirmed
publications.
The paper is organized as follows: first, we outline the related works and then pre-
sent the essential datasets and metadata. After that, the matching and clustering algo-
rithm and implementation details are described. Finally, we demonstrate an interac-
tive visualization, which facilitates the comprehension of the matching and clustering
results and allows users to improve them.
2 Related Works
Entity resolution – identity resolution, deduplication, record linkage, object matching
– refers to the task of identifying different representations of the same real-world
object. In the context of relational data bases, the term entity reconciliation has been
used for a long time. Another related term is link discovery, which describes the pro-
cess of automatic search for the overlapping parts of heterogeneous data sets and link-
ing individual records of these data sets by exploiting their specific properties. When
talking about entities from multiple sources, it is common to use the term entity clus-
tering. There are several groups of works closely related to the topic of our paper.
Entity resolution is an important step in any data integration pipeline as well as in
the area of information retrieval and question answering. Nowadays, data from any
domain are available on the Web and a lot of research has been dedicated to this prob-
lem. A recent overview is presented in [11]. A semantic data integration technique
exploiting the semantics encoded in the properties of the entities collected from the
Web data sources is implemented in FuhSeh query engine [12]. FuhSeh receives
keyword based queries and produces knowledge graphs on demand at query time,
making use of wrappers around the original data sources to generate RDF molecules
and to merge several RDF molecules into a single one [13]. For more than two
sources, a binary linking of entities is not sufficient: all matches of the same entity
should be clustered together to derive a fused entity representation in the knowledge
graph. Clustering is applied on a similarity graph, where entities are represented as
29
vertices and edges link pairs of entities with a similarity above a predefined threshold.
An approach to entity linking in multiple data sources is described in [14].
To avoid comparing new entities with all members of existing clusters, each cluster
creates a cluster representative, which is fused from all the properties of the cluster
members. The same idea is implemented as the DBpedia Global Id Management
module [15], which assigns a global cluster ID to the entities linked by owl:sameAs
links in different language editions of DBpedia. However, it is known that the number
of the explicit inter-language links does not exceed 15 percent of the existing links.
Therefore, much more numerous are the studies of cross-lingual KG alignment
aiming to match automatically entities in different languages from different data
sources. Recently, several embedding-based approaches have been proposed for
cross-lingual KG alignment, including MTransE [16] and JAPE [17].
More recent papers model the equivalent relations between entities by using the
graph convolutional networks (GCN), since they are able to generate the neighbor-
hood-aware embeddings of entities used to discover entity alignments [18].
Unlike the previous methods using entity embeddings to match entities, the paper
[19] formulates the task of entity matching as a graph matching problem between the
topic entity graphs. The latter approach is somewhat similar to the RDF-molecule
based approach discussed in [13]. Finally, of special interest is the paper [20] describ-
ing an experience of interlinking the SN SciGraph with the English edition of DBpe-
dia. However, none of these approaches takes into consideration different translitera-
tions that may correspond to an entity having the same name.
3 Datasets and Their Metadata
The SpringerLink digital library [21] has been chosen as an English-language biblio-
graphic data source mainly because of its continuously expanding set of metadata.
SpringerLink is currently one of the largest digital libraries with over 13 million doc-
uments in various research fields including computer science, mathematics, life sci-
ences, materials, philosophy, psychology, etc. It provides detailed meta-data about its
publications, such as the paper title, list of authors, ISSN, authors’ affiliations, publi-
cation date, venue (journal or conference title), key words, subject abstract, refer-
ences, full texts in pdf format, etc. One of the recent innovations is the “translated
from” label for the papers written in foreign languages. This additional data makes it
possible to improve the disambiguation quality by matching the data of the original
and translated paper versions.
Other important reasons for choosing this data source are open access to its data
and the emergence of the related SN SciGraph Linked Open Data platform, which
also demonstrates the problems mentioned above.
The eLIBRARY.ru data base is the largest bibliographic data set used for compu-
ting the scientific rating of Russian researchers. eLIBRARY.ru stores data in the
fields of science, technology, medicine and education on more than thirty million
publications, more than 900,000 researchers and over 13,000 organizations (including
over 3,000 officially registered). The A.P. Ershov Institute of Informatics Systems of
30
the Siberian Branch of the Russian Academy of Sciences is an organization registered
at eLIBRARY.ru; it regularly inputs and updates information concerning its employ-
ees’ publications. Moreover, you can find here a complete list of publications by
Academician Andrei Petrovich Ershov created by Anna Andreyevna Bulyonkova.
The sets of metadata provided by eLIBRARY.ru are similar to those of Spring-
erLink, though access to these metadata is restricted. To be more specific, the list of
publications of an author is freely available, but detailed metadata on his/her papers
are not free. Therefore, our disambiguation algorithm is based on the data freely
available at eLIBRARY.ru. Another essential difference between these two data
sources is that the language of SpringerLink is English, and that of eLIBRARY.ru is
Russian, even when it stores data on the English publications of Russian researchers.
The main problem, hence, is how to match entities described in different languages.
4 Problem Formulation and Algorithm to solve It
The problem to solve is formulated as follows. Given an English language biblio-
graphic data source(s), extract all publications potentially belonging to the person(s)
specified by a Russian-language keyword and divide the extracted articles into subsets
S1, S2, ..., Sn so that each subset of articles belongs to one real person.
The steps of the matching and clustering algorithm are:
1. Given a full Russian name, a set of extended transliterations is generated.
2. Elements of this set are used for the keyword search of publications in the English-
language data source (for example, SpringerLink digital library).
3. An extended set of potential homonyms of the person, specified by the full Russian
name, is used to extract groups of publications from a Russia-language data source
(for example, eLIBRARY.ru).
4. All the publications extracted from SpringerLink are matched against the eLI-
BRARY.ru groups of publications.
5. The papers unmatched at the previous step are further analyzed and clustered.
6. Interactive visualization of the clustering results makes it possible to analyze and to
further refine it.
The extended transliteration and data extraction from the English-language source
SpringerLink are described in detail in [3]. Therefore, we will describe in more detail
creating the groups of confirmed publications, a clustering algorithm, and interactive
visualization.
The authors of the publications extracted from SpringerLink can be either homo-
nyms or synonyms. The entity identification algorithm should process the list of pub-
lications and determine which of their authors are synonyms and which are homo-
nyms. In other words, the list of publications should be clustered into the subsets S1,
S2,…, Sn such that each subset of articles is authored by a single person and all his or
her name variations are synonyms. The subset S1 should contain the articles authored
by the person under consideration.
31
To this end, the list of publications S extracted from SpringerLink is matched
against the lists of publications E extracted from eLIBRARY.ru. Note that the papers
of eLIBRARY.ru are already clustered into the groups E1, E2,…, Em corresponding to
individual authors. Therefore, if a paper si S is recognized as identical to a paper ej
belonging to a group Em from eLIBRARY.ru, it is assigned to a group Sm.
eLIBRARY.ru specifies persons by their full Russian name in format, affiliation and location of the employing organization.
Note that each person can have several homonyms and “partial” homonyms, when
a short form of his/her name coincides with the short form of another person’s name.
For example, five full homonyms, having the same name Петров Евгений
Сергеевич, are described in eLIBRARY.ru along with two partial homonyms having
two distinct middle names. The persons having identical full or short forms of their
names can be erroneously identified as synonyms.
To prevent this kind of errors, our algorithm creates groups of confirmed eLI-
BRARY.ru papers for each potential homonym of a given author. Since we consider
eLIBRARY.ru to be a reliable source of information about publications written by
Russian authors, we use it to create confirmed groups of publications for an English
data source. That is why the confirmed groups of papers are created by comparing the
papers from SpringerLink and eLIBRARY.ru.
When comparing publications from the two data sources, two main possibilities are
considered.
1. Publications in both data sources are described in English. The situation when a
publication in eLIBRARY.ru contains a description in Russian and an English-
language version of the publication is described in the "Versions" field of the pub-
lication also falls into this category.
2. The English data source contains an English description of the publication, and
the Russian data source only contains a description of the Russian version.
In the first case, when the descriptions of both articles are given in English, the
names of the publications and the lists of authors are compared. A paper si S is con-
sidered to be identical to a paper ej E if Title(si) = Title (ei) AND Authors(si) = Au-
thors(ei). The title cannot identify a paper uniquely as some authors can have several
publications with the same title. Nevertheless, the exact match of titles and author
names can be considered as evidence that the papers were authored by the same per-
son. However, some paper titles differ in SpringerLink and eLIBRARY.ru due to
scanning errors. For example, the paper titled as SCHEMATOLOGY IN A MULTI-
LANGUAGE OPTIMIZER in eLIBRARY.ru appears as Schematology in a MJ I/T I-
language OPT imizer in SpringerLink. In the absence of an exact match of the paper
titles, both titles are stemmed by the Porter stemmer and their overlap score is calcu-
lated. If this score exceeds a threshold value, the titles are considered coinciding. The
discovered matching is written in a special file for further user control.
In the second case, cross-language identification of paper and journal titles should
be applied. Many Russian journals are first published in Russian and then translated
in English. A typical example is the Программирование journal, which is published
in English as Programming and Computer Software. About 40% of eLIBRARY.ru
32
older entries have only Russian description and do not have an English counterpart.
These publications, however, are very important for making confirmed paper groups
as large as possible. This situation raises several problems. First, it is impossible to
compare papers by the title when the title of an original paper is in Russian and the
title of a translated paper is in English. Besides, the original and translated papers
have disjoint sets of attributes, such as venue, ISSN, publication data, page numbers,
etc.
Although SpringerLink provides information about the journal titles in the Latin
alphabet only, every translated paper in the database mentions its Russian original.
For example, the paper by V.E. Kotov Parallel programming with types of control
has the label “Translated from Kibernetika, No. 3, pp. 1–13, May-June, 1979” in
SpringerLink. Moreover, the SpringerLink database provides the ISSN of the trans-
lated version. This information suffices to find the Russian version of the paper if it is
available in eLIBRARY.ru. The corresponding English-language article is marked as
matched and the pair of papers is saved for further processing.
The average number of papers assigned to the confirmed groups during the match-
ing step was about 69%, while the number of erroneously attributed publications was
close to zero. The main reason why the system cannot assign some papers to their
authors is data sparsity. To extend the set of the identified authors of papers, a cluster-
ing algorithm was applied to the unmatched papers.
5 Unmatched Papers Clustering
The publications unmatched at the previous step are considered to be unconfirmed
and should be further analyzed and clustered. The clustering algorithm for uncon-
firmed publications is based on comparing each unconfirmed publication with groups
of confirmed publications based on various similarity metrics.
The unconfirmed publications are compared with groups of confirmed publications
using the following attributes: titles of publications, lists of authors of publications,
topics and keywords, dates of publication, venue of publication (journal title or con-
ference title), and similarity of texts of publications (TF-IDF).
All the attributes are compared pair wise, which results in a number of scores that
are summarized in the final step. When calculating the similarity scores the program
adheres to the following rules.
Titles of papers similarity If an exact match of the paper titles A and B is found,
the title_similarity_score is set to 1.0. Otherwise, the titles of the papers A and B are
stemmed, and the title_similarity_score is set to the overlap ratio of their word lists.
Co-authors similarity For each confirmed group of publications, a list of all its
co-authors is created, and the more often an author appears in the list of co-authors for
a certain group of publications, the greater is his weight. Also, for each confirmed
group of publications, a list of the author’s affiliations is created, which characterizes
each group, and when comparing the authors of publications, not only the names of
the authors, but also their affiliations are compared.
33
Subjects and keywords similarity The subject_similarity_score and key-
word_similarity_score use Jaccard Index to evaluate the overlap ratio of the respec-
tive lists.
Date similarity The date_similarity_score is set to 0.1 if the timestamp difference
of the papers A and B is less than five years. If the timestamps difference of the pa-
pers A and B is more than twenty five years, it is set to - 0.1.
Venue similarity The publication_venue_score (i.e., conference/journal title) is set
to 0.1 if there is an exact match between their titles.
Text similarity Text_similarity_score is evaluated by TF_IDF and cosin similarity
measure.
The final assignment likelihood is calculated as the sum of all the above scores.
All unconfirmed publications initially obtain a group number of -1. An uncon-
firmed publication joins a group of confirmed publications if its similarity with a giv-
en group exceeds a threshold value. Two groups of unconfirmed publications can be
merged if the similarity value of publications inside two groups exceeds the threshold
value. When merging two groups, the algorithm monitors that both groups do not
belong to the set of the confirmed groups. If this happens, the merging does not occur,
since the confirmed groups correspond to the publications by distinct authors. The
weights of all the attributes involved in the comparison, as well as the threshold
value, can be adjusted at the stage of interactive visualization.
6 Interactive Visualization for Analyzing and Modifying the
Matching and Clustering Results
To simplify the understanding and modification of the matching and clustering re-
sults, several interlinked visualizations have been developed; they are described in
detail in [4]. A global view of the obtained groups of publications is represented as a
pie chart. An example of the pie chart produced by using the full Russian name
Валерий Александрович Непомнящий is shown in Fig. 1. Each segment of the pie
chart corresponds to a separate group of publications attributed to a single author. The
size of a segment in the pie chart is proportional to the number of documents assigned
to this group. A short textual description of a chosen documents group appears after a
mouse click on a segment of the pie chart in the right panel.
Experiments have shown that to verify the matching and clustering results users
need to compare papers clustered in distinct groups. To this end they need to see all
the attributes of the entire set of publications in a single view. Therefore, a set of vis-
ualizations was extended by a similarity matrix reordering module based on the reor-
der.js library [22]. The reorder.js library comprises several matrix reordering algo-
rithms
34
Fig. 1. The clustering result produced when using the full Russian name Валерий
Александрович Непомнящий as a keyword.
Fig. 2. Groups of publications created by the Leaf Order method for a similarity matrix pro-
duced by our matching and clustering algorithm.
such as Barycenter heuristic, Optimal Leaf Ordering, Principal Component Analysis,
Reverse Cuthill-McKee, and Spectral Ordering. An example of visualization created
35
by the similarity matrix ordering module is shown in Fig. 2. All publications assigned
to the same group by our matching and clustering algorithm have the same color.
When selecting an entry of the similarity matrix with the mouse, user can get com-
plete information about all the attributes of the two compared publications and all the
terms of their similarity score. The diagonal blocks of similarity matrices correspond
to groups of publications that are most similar to each other. The matrix ordering
module uses the same similarity values as our clustering algorithm implemented in
the matching and clustering program.
Two groups of experiments have been carried out. First, the available matrix order-
ing algorithms were applied to the similarity matrices, which contained information
about the similarity of various publications in the English source, but did not contain
information about the results of the comparison of the English-language and Russian-
language data sources. In this case, all ordering algorithms showed different results.
Then the similarity matrices have been modified by adding a large similarity score
to the publications that were classified as identical at the stage of the comparison of
the English-language and Russian-language data sources. After that, all the matrix
ordering algorithms have started to output the equivalent results.
7 Conclusion
The newly developed matching procedure provides the algorithm presented in this
paper with the ability not only to cluster the papers correctly, but also to determine the
exact identity of authors, including the name and location of the affiliating organiza-
tion.
The program implementing the algorithm has been tested on a dataset of 100 per-
sons employed by the IIS SB RAS at various time periods. Also, this dataset contains
Academician A.P. Ershov, whose papers have been input into eLIBRARY.ru by the
IIS SB RAS. The total number of papers found in SpringerLink for all Russian names
in this dataset was 3,175. All the results obtained by the program were verified manu-
ally. For each person listed in the test dataset the following values were calculated:
total number of papers found in SpringerLink for each Russian full name listed in
the test dataset;
number of articles actually authored by a researcher specified in the test dataset;
number of papers that have been correctly recognized by the matching algorithm;
number of papers that have been correctly recognized by the matching + clustering
algorithm;
Experiments have shown that the main source of improving the quality of cross-
lingual entity resolution algorithm is extending the set of confirmed publications by
matching publications and authors in Russian and English data sources. The combina-
tion of the matching algorithm and the clustering algorithm allows us to correctly
recognize from 92 to 93 percent of publications.
This algorithm can be used to match any multilingual knowledge bases. The fur-
ther development of these studies is supposed to focus on implementing new algo-
rithms for the cross-language identification of entities and on implementing a full-
36
fledged framework including tools for accessing various data sources, methods for
establishing correspondence between different schemes of data sources, etc.
The author thanks Avramenko M.Yu., Paramoshin A.A., Isachenko V.V., and
Eliseev E.S. for participating in the implementation of the various versions of the
matching and clustering algorithm.
References
1. Reijnhoudt, L., Costas, R., Noyons, E., Boerner, K., Scharnhorst, A. "Seed+ expand": A
validated methodology for creating high quality publication oeuvres of individual re-
searchers. In: Proceedings of ISSI 2013 Vienna, arXiv:1301.5177 (2013).
2. Lawrie, D., Mayfield, J., McNamee, P., Oard, D.W.: Cross-Language Person-Entity Link-
ing from Twenty Languages (2015).
3. Apanovich, Z., Marchuk, A.: Experiments on Russian-English Identity Resolution. In: Al-
len R., Hunter J., Zeng M. (eds) Digital Libraries: Providing Quality Information. ICADL
2015. Lecture Notes in Computer Science, vol. 9469. Springer, Cham (2015).
4. Apanovich, Z., Isachenko, V.: Analysis and visualization algorithm for cross-language au-
thor names disambiguation. In: Proceedings of the XX International Conference “Data
Analytics and Management in Data Intensive Domains” (DAMDID/RCDL’2018), Mos-
cow, Russia, October 9–12, pp. 277–283 (2018).
5. Scopus Homepage, https://www.scopus.com, last accessed 2019/11/20.
6. eLIBRARY.ru Homepage, https://elibrary.ru, last accessed 2019/11/20.
7. Izaak, A.D., Znamenskaia, E.A., Chebukov, D.E.: O poteriannykh tsitirovaniiakh v Web of
Science i ikh vliiaii na impakt-faktory zhurnalov. In: Nauchnyi servis v seti Inter-
net 20 (20), 238–243 (2018).
8. ORCID Homepage, http://orcid.org, last accessed 2019/11/20.
9. SN SciGraph Homepage, https://www.springernature.com/gp/researchers/scigraph, last ac-
cessed 2019/11/20.
10. GRID Homepage, https:/www.grid.ac, last accessed 2019/11/20.
11. Nentwig, M., Hartung, M., Ngomo, A.C.N., Rahm, E.: A survey of current link discovery
frameworks. Semant. Web 8, 419–436 (2017).
12. Collarana, D., Lange, C., Auer, S.: FuhSen: a platform for federated, RDF-based hybrid
search. In: Proceedings of the 25th International Conference on World Wide Web,
pp. 171–174 (2016).
13. Collarana, D., Galkin, M., Lange, C., Scerri, S., Auer, S., Vidal, M.E.: Synthesizing
Knowledge Graphs from Web Sources with the MINTE+ Framework. In: Vrandečić D. et
al. (eds) The Semantic Web – ISWC 2018. ISWC 2018. Lecture Notes in Computer Sci-
ence, vol. 11137. Springer, Cham (2018).
14. Saeedi, A., Peukert, E., Rahm, E.: Using Link Features for Entity Clustering in Knowledge
Graphs. In: Gangemi A. et al. (eds) The Semantic Web. ESWC 2018. Lecture Notes in
Computer Science, vol 10843. Springer, Cham (2018).
15. Frey, J., Hofer, M., Obraczka, D., Lehmann, J., Hellmann, S.: DBpedia FlexiFusion the
Best of Wikipedia > Wikidata > Your Data. In: Ghidini C. et al. (eds) The Semantic Web –
ISWC 2019. ISWC 2019. Lecture Notes in Computer Science, vol. 11779. Springer, Cham
(2019).
16. Chen, M., Tian, Y., Yang, M., and Zaniolo, C.: Multilingual knowledge graph embeddings
for cross-lingual knowledge alignment. arXiv preprint arXiv:1611.03954 (2016).
37
17. Sun, Z., Hu, W., and Li, C.: Cross-lingual entity alignment via joint attribute-preserving
embedding. In: International Semantic Web Conference, pp. 628–644. Springer (2017).
18. Wang, Z., Lv, Q., Lan, X., and Zhang, Y.: Cross-lingual knowledge graph alignment via
graph convolutional networks. In: Proceedings of the 2018 Conference on Empiri-
calMethods in Natural Language Processing, p. 349–35 (2018).
19. Xu, K., Wang, L., Yu, M., Feng, Y., Song, Y., Wang, Z., Yu, D.: Cross-lingual Knowledge
Graph Alignment via Graph Matching Neural Network https://arxiv.org/pdf/
1905.11605v3.pdf (2019), last accessed 2019/11/20.
20. Yaman, B., Pasin, M., Freudenberg, M.: Interlinking SciGraph and DBpedia Datasets Us-
ing Link Discovery and Named Entity Recognition Techniques In:2nd Conference on
Language, Data and Knowledge (LDK 2019). Editors: Maria Eskevich, Gerard de Melo,
Christian Fäth, John P. McCrae, Paul Buitelaar, Christian Chiarcos, Bettina Klimek, and
Milan Dojchinovski; Article No. 15; pp. 15:1–15:8 OpenAccess Series in Informatics
Schloss Dagstuhl – Leibniz-Zentrum für Informatik, Dagstuhl Publishing, Germany
(2019).
21. SpringerLink digital library Homepage, https://link.springer.com/, last accessed
2019/11/20.
22. Fekete, J.-D.: Reorder.js: A JavaScript Library to Reorder Tables and Networks. In: IEEE
VIS 2015, Oct 2015, Chicago, United States (2015).