=Paper=
{{Paper
|id=Vol-2788/om2020_Tpaper1
|storemode=property
|title=Using domain lexicon and grammar for ontology matching
|pdfUrl=https://ceur-ws.org/Vol-2788/om2020_LTpaper1.pdf
|volume=Vol-2788
|authors=Francisco José Quesada Real,Gábor Bella,Fiona McNeill,Alan Bundy
|dblpUrl=https://dblp.org/rec/conf/semweb/RealBMB20
}}
==Using domain lexicon and grammar for ontology matching==
https://ceur-ws.org/Vol-2788/om2020_LTpaper1.pdf
Using Domain Lexicon and Grammar
for Ontology Matching
Francisco José Quesada Real1,2 , Gábor Bella3 ,
Fiona McNeill1 , and Alan Bundy1
1
University of Edinburgh, UK
{s1580097,fmcneill,a.bundy}@ed.ac.uk
2
University of Cádiz, Spain
franciscojose.quesada@uca.es
3
University of Trento, Italy
gabor.bella@unitn.it
Abstract. There are multiple ontology matching approaches that
use domain-specific background knowledge to match labels in domain
ontologies or classifications. However, they tend to rely on lexical
knowledge and do not consider the specificities of domain grammar.
In this paper, we demonstrate the usefulness of both lexical and
grammatical linguistic domain knowledge for ontology matching through
examples from multiple domains. We also provide an evaluation of
the impact of such knowledge on a real-world problem of matching
classifications of mental illnesses from the health domain. Our
experimentation with two matcher tools that use very different matching
mechanisms—LogMap and SMATCH—shows that both lexical and
grammatical knowledge improve matching results.
Keywords: Ontology Matching · Domain-Knowledge · Domain
Language · Domain Lexicon · Domain Grammar
1 Introduction
Ontology Matching (OM) aims at finding correspondences between the classes
and instances of multiple ontologies [10]. Thus, OM processes are commonly
carried out to solve heterogeneity problems that occur when multiple knowledge
resources need to be integrated or used together. Among common approaches
used in OM, the comparison of node labels has been one of the most performant
and widely used techniques. While label matching has been addressed by
the earliest matchers through simple methods such as string similarity, more
complex cases such as syonymy, cross-lingual, or domain-specific matching need
linguistically better-founded solutions [3]. The problem of matching domain
ontologies or classifications is special because labels tend to mix elements of
the general language with domain terms, and sometimes even grammatical
Copyright c 2020 for this paper by its authors. Use permitted under Creative
Commons License Attribution 4.0 International (CC BY 4.0).
2 Quesada et al.
forms that are domain-specific. In cross-domain matching scenarios, phenomena
of meaning shifts, polysemy, and synonymy make the matching task even
harder, such as in the emergency response domain where subdomains of police,
healthcare, fire brigades, etc., need to be aligned [17, 18]. Another example is that
of mapping standard classifications within the healthcare domain that, despite
relying on precise domain terminology, express the same concepts in different
ways, such as ‘rupture of aorta’ versus ‘aortic aneurysm, ruptured’. Establishing
precise mappings across standards has a major importance for cross-border
health applications as they enable automated data integration methods [6].
A large number of matchers analyse natural language labels, on different
levels of complexity. A common approach is to incorporate linguistic background
knowledge (BK) into the matcher [9, 10].
SMATCH [14] relies on domain-independent BK: it uses WordNet [12]
as an English domain-independent lexical database, and analyses labels
using general grammatical tools such as tokeniser, lemmatiser, and syntactic
parser. Other matchers, such as LogMap [15] or YAM-BIO [2], have been
customised to integrate domain terminology to address specific matching
challenges, such as biomedical terms. This results in increased performance
on domain-specific matching; however, the longer the labels become, the more
likely their grammatical structures and their use of general language become
important, which cannot be covered by terminological knowledge alone. For
this reason, some matchers, such as AML [11] or ALIN [8], integrate both
domain-independent and domain-specific knowledge (e.g. WordNet together with
biomedical resources).
All of these matchers, however, are limited to using lexical BK. While
some of them do address grammar through basic domain-independent methods
(tokenisation, lemmatisation, stop word elimination), they do not cope with cases
where the grammar depends on the domain.
In this paper, we investigate the impact of both domain lexicon and domain
grammar in ontology matching, mainly focusing on label-based matching.
The paper is organised as follows. In Section 2 we describe how domain
knowledge appears in ontology labels. Section 3 focusses on different approaches
that matchers may use to take advantage of domain knowledge. A case study
on the health domain is presented in section 4, being evaluated in section 5.
The paper finishes with some concluding remarks and future works included in
section 6.
2 Domain Language in Ontology Labels
The use of specialised linguistic constructs is common in most domains of
knowledge. The most obvious case is the use of specialised terminology, consisting
of words and expressions that either are used exclusively within the context of
a domain (such as to deglaze in cooking meaning ‘to loosen bits of food which
stuck on the bottom of a pan by adding liquid’ ), or that gain a new meaning
within a domain (such as to clarify which in cooking refers specifically to butter).
Using Domain Lexicon and Grammar for Ontology Matching 3
Domain-specific meaning can, however, also be vehicled by non-lexical means,
a phenomenon that we globally call domain grammar. Domain grammar can
be found even within the short labels typical of ontologies and classifications.
Below we provide examples of domain language from specialised text, including
ontology labels.
Domain terms. The UK Civil & Protection Lexicon (UKCP) defines the term
medevac that means medical evacuation, itself considered a specialised term. In
order to align these two terms, a matcher would either need lexical background
knowledge that states their synonymy, or—in this specific case—word-level
analysis in order to detect that one term is the abbreviated form of the other.
Domain acronyms. The acronym REM has many meanings; in the domain of
neurology it means rapid eye movement. Again, in a matching task the acronym
can be matched either through the use of domain lexical knowledge or through
acronym detection.
Word derivation. Derivation rules allow the creation of words through the
use of affixes, such as voyeur 7→ voyeurism or anorexia 7→ anorexic. While,
as in these cases, domain language often relies on the derivational rules of
general grammar, domain-specific derivational affixes and rules also exist, such
as candida 7→ candidiasis in the medical domain. Even though the common
approach in lexicography is to enumerate derived words as separate lexical
entries, lexicons are often incomplete in practice due to the high productivity
of affixes. Thus, grammar-based approaches to detecting the relatedness of
derived terms can be useful, as when matching the label fetishism with fetishistic
disorder.
Word inflection. Inflection rules are defined by general language; yet, particular
inflected forms can be more or less specific to domains. A well-known example
are cooking recipes where sentences tend to begin with verbs either in infinitive
or imperative form (e.g. ‘Peel the onions’, which in French may be expressed
either as ‘Peler les ognons’ or as ‘Pelez les ognons’ ).
Specific uses of punctuation. In labels of the International Classification
of Diseases (ICD), such as ‘Hallucinogen use, unspecified with hallucinogen
persisting perception disorder (flashbacks)’, parentheses are used to provide clues
for the interpretation of the label. Square brackets, commas, or parentheses
are also widely used in ontologies, classifications, and data schemas, such as
to provide units of measure for numerical values: speed (km/h). The precise
interpretation (e.g. relevance or not with respect to the matching task) of such
punctuation and the text they delimit depends on the domain and the particular
application at hand.
Domain syntax. The same ‘Hallucinogen use. . . ’ example from above shows that
labels can use non-standard syntax. This is sometimes motivated by the context
of use, such as the need to sort the labels alphabetically motivates the use of the
adjective unspecified in a postpositive form. The phrase hallucinogen persisting
4 Quesada et al.
perception disorder, on the other hand, includes syntax that is not considered as
standard in general language but is common in medical text. While syntax may
play a minor role in matching very short labels, for longer classification entries
it may be taken into account by the matcher tool, as in the case of SMATCH
that performs syntactic parsing.
3 Leveraging Domain Language for Ontology Matching
The hypothesis verified in this paper is that “matching performance can
be improved by relying on knowledge that is specific to domain language”.
However, as domain language also incorporates elements of general language, our
study also considers this aspect. Accordingly, we classify linguistic background
knowledge with respect to being general or domain-specific, as well as with
respect to being lexical or grammatical. This delineates the following four
categories of knowledge: (1) general lexicon; (2) general grammar; (3) domain
lexicon; and (4) domain grammar. Furthermore, we consider three different forms
of grammatical knowledge with respect to the linguistic elements to which they
apply: (a) phrase-level (syntax, dealing with the way words are organised within
labels); (b) word-level (morphology, i.e. grammar that deals with the structure
of words); and (c) character-level (e.g. orthography and use of punctuation).
Due to the shortness of ontology and classification labels, we deem it sufficient
to consider only these three levels of granularity of grammar.
General Lexicon A domain-independent resource that is commonly used is
Princeton WordNet [12] which is a lexical database in which nouns, verbs,
adjectives and adverbs are grouped into sets of synonyms, each expressing a
different concept. All sets are semantically related between them with an is a
relationship, forming a taxonomy, in which the more general elements are at the
top and the more specific are at the bottom levels.
Domain Lexicon There are multiple domain-specific resources such as lexicons
or domain terminologies that contain the technical terms of an specific domain.
In the literature, we can find different approaches to integrating these resources
within WordNet [1, 17]. Their main goal is to append specialised knowledge
to general knowledge currently represented in WordNet (e.g. coronavirus
as a specialised type of infection). However there are cases in which the
current representation of a word in WordNet differs from its meaning in the
domain-specific resource (e.g. evacuation in WordNet and in the UKCP). In
these cases, the integration is more complex and needs to be done in a supervised
way [17].
The main advantage of using domain lexical knowledge is that matchers have
an enriched BK and are able to find mappings of labels that include some of the
added new terms. Moreover, when matching ontologies from multiple or partially
different domains (such as reference health knowledge involving subdomains of
healthcare), domain information can be leveraged for word sense disambiguation
within the matching process, resulting in improved precision [5].
Using Domain Lexicon and Grammar for Ontology Matching 5
General Grammar Most matchers consider the grammar within labels for the
matching process. In this case, they carry out some of the following tasks with
independence from the domain of the resources to be matched [10].
– Phrase Level Grammar .
• Tokenisation. Labels are segmented into tokens (e.g. “medium-scale
evacuation” becomes ).
• Acronym extraction. Characters of tokens are used to extract/discover
acronyms (e.g. “Non Governmental Organisation” becomes “NGO”).
• String similarity. Compare string labels considering different measures
and return a value according to their similarity degree (e.g. “Level of
emergency” and “Level 1 emergency” have a high similarity degree).
• Stopword elimination. Tokens that are recognised as articles,
prepositions, conjunctions are removed (e.g. “level of emergency”
becomes “level emergency”).
– Word Level Grammar .
• Lemmatisation. Tokens are reduced to basic forms (e.g. “disasters”
becomes “disaster ”).
– Character Level Grammar .
• Normalisation. This task includes several subtasks such as: case
normalisation, diacritics suppression, blank normalisation, digit
suppression or punctuation elimination.
Domain Grammar There are cases in which applying the previous
domain-independent tasks to domain-specific resources is counter-productive.
For example, if we apply digit suppression and stopword elimination to
the following labels: “Level of emergency”, “Level 1 emergency”, “Level 2
emergency”, “Level 3 emergency”; the matcher might output that all labels
represent the same knowledge. Another example appears when the case
normalisation task is just limited to transform all characters within the label into
lower case letters. In this case, if the label contains Roman numerals they might
pass unnoticed after the case normalisation. For these reasons, it is necessary
to consider domain-specific grammar and address it conscientiously. Below there
are described the approaches that we have implemented in our research:
– Phrase Level Grammar . Finding clues or postscripts that recurrently appear
within the labels in a domain is not unusual. In this case, it is necessary
to analyse if they add enough knowledge to keep them in the label or it is
worth suppressing them (e.g. “Mild cognitive impairment( , so
h hstated”).
( h(
( h(h
– Word Level Grammar . Implementing derivational morphology rules to
transform a term from one part-of-speech into another is interesting because
enriching matchers’ BK with these words allows those matchers that do not
mainly base the matching process on string similarity measures to discover
new mappings. Domain words produced by derivational morphology are
added to matchers’ BK as related forms (e.g. “pathological ” is added as
a related form of “pathology).
6 Quesada et al.
– Character Level Grammar . Depending on the domain, particularly in
application domain knowledge resources, orthography follows different
conventions. This makes necessary to address it optimally in each case. For
example, there might be cases in which the content within parentheses or
square brackets is meta-information that is not relevant for the meaning of
the label (e.g. “Post(-) traumatic stress disorder ”), being recommendable
its suppression, whereas in other cases this content might be essential (e.g.
“Stable lodine (Potassium lodate tables)”).
The rules of the different domain grammar levels can be extracted both in a
supervised or unsupervised way. The latter requires a huge number of documents
to apply statistical methods, whereas the former does not need such quantity of
documents, but involves more effort. In general, the rules at the word level can
be transferred to any ontology within a domain (e.g. health), while the rules at
the phrase and character levels usually are more dependent on the application
domain (e.g. Hospitals of North London).
4 Case Study on the Health Domain
The main motivation lies in the need of solving semantic interoperability
problems within the health domain. For example, when clinicians have
to exchange health records that contain descriptions from multiple official
classifications of diseases. To do so, we have developed several extensions to
enrich the matcher’s BK with health lexical and grammatical knowledge.
Due to descriptions of disorders containing not only technical, but also
general terms, WordNet has been used as a domain-independent BK into which
the extensions are plugged. The extensions have been developed following the
Lexical Markup Framework (LMF) standard [13], and integrated into WordNet
using Diversicon [4], which is a framework that allows extending WordNet with
any domain-specific knowledge represented in LMF, validating and generating
an enriched WordNet.
General Lexicon Princeton WordNet has been used as domain-independent
resource. The main reason is that it represents general knowledge and there are
multiple approaches that we could apply to enrich WordNet with domain-specific
knowledge resources.
Health Domain Lexicon We have developed an extension for WordNet that
includes health lexical knowledge extracted from the following resources:
– MeSH is the National Library of Medicine’s controlled vocabulary thesaurus
[16]. It consists of sets of terms, naming descriptions, in a hierarchical
structure that permits searching at various levels of specificity. The hierarchy
is sorted considering several semantic relations such as is a or part of. This
hierarchy is similar to the way in which WordNet is organised, which makes
easier its integration. The developed extension for WordNet contains all
Using Domain Lexicon and Grammar for Ontology Matching 7
descriptions included in the “Diseases” and “Psychiatry and Psychology”
MeSH categories. In this case, we only consider the is a semantic relation,
because we have detected several problems using part of when matching
diseases (e.g. a “heel disease” is a “foot disease”, but an “eye disease” is
not a “face disease”). Addressing these problems is something that we are
considering as a future work.
– The SPECIALIST lexicon is an English lexicon which contains both
commonly occurring English words and biomedical vocabulary [7]. It is
composed of lexical records, being each of them formed by a base form
and a set of spelling variants or morphological derivations. For example,
the lexical entry with base “nephroprotective” (adj) has as spelling variant:
“nephro-protective”, and as morphological derivation “nephroprotectivity”
(noun). This resource has been used for enriching matchers’ BK lexically,
through developing an extension for WordNet that contains all lexical entries
included in SPECIALIST.
General Grammar It has been addressed applying the grammatical techniques
included in the matchers by default and including general derivational
morphology.
Phrase level Grammar. The tasks applied have been: tokenisation, string
similarity and stop word elimination.
Word level Grammar. In this case we applied lemmatisation and the integration
of general derivational morphology rules included in SPECIALIST. Table 1
shows examples of these rules.
Table 1. General derivational morphology rules.
Derivational rule Example
iency$(noun) → ient$(adj) immuno-deficiency(noun) → immuno-deficient(adj)
sation$(noun) → zed$(adj) anesthetisation(noun) → anesthetized(adj)
ical$(adj) → y$(noun) uroradiological(adj) → uroradiology(noun)
ism$(noun) → istic$(adj) fetichism(noun) → fetichistic(adj)
Character level Grammar. The tasks applied have been case normalisation, blank
normalisation and diacritics suppression.
Health Domain Grammar It has been addressed using health derivational
morphology extracted from SPECIALIST, and considerations identified at
phrase and character grammar levels. The former was used to enrich matchers’
BK, whereas the latter were considered as a preprocessing step prior to the OM
process.
Phrase level Grammar. In medical resources there are clues that recurrently
appear within descriptions of disorders. Examples are “, undefined ” and “, so
stated ”. This meta-information does not add special value to labels, particularly
affecting to those matchers that mainly use string similarity measures. The main
reason is that they are penalised by irrelevant characters, which results in a lower
8 Quesada et al.
similarity degree. Considering the previous issue we decided to suppress these
interpretational clues from descriptions of diseases in a preprocessing step prior
to the matching process.
Word level Grammar. Several domain-specific derivational morphology rules
have been extracted from the SPECIALIST lexicon and integrated into
WordNet. Examples of these rules are shown in table 2.
Table 2. Health derivational morphology rules.
Derivational rule Example
ose$(verb)→ osis$(noun) sclerose(verb) → sclerosis(noun)
physeal$(adj) → physis$(noun) adenohypophyseal(adj) → adenohypophysis(noun)
sis$(noun)→ ze$(verb) dialysis(noun) → dialyze(verb)
a$(noun)→ iasis$(noun) candida(noun) → candidiasis(noun)
Character level Grammar. We have identified a particular use of parentheses,
square brackets and commas in the health domain. Examples of the use of
parentheses and square brackets might be the following:
1. Sleep terrors [night terrors]
2. No Diagnosis or Condition on Axis I / No Diagnosis on Axis II [DSM-IV]
3. Premature (early) ejaculation
4. Trichotillomania (hair-pulling disorder)
5. Obstructive sleep apnea (adult) (pediatric)
In case 1, the square brackets are used to specify an equivalent expression of
“sleep terrors”. Similarly, in case 3 parentheses are used to indicate a synonym
of “premature”. Case 2 is different as brackets are used to point out the DSM
version in which the description was included. In case 4 the content within
parentheses categorises the kind of disorder that “trichotillomania” is. Finally,
case 5 uses parentheses to indicate the domain to which the disorder is applicable,
in that case to adults and children.
Similarly as in the previous cases, commas are utilised with different purposes
in the medical knowledge. Below there are some examples:
1. Tobacco use disorder, Mild
2. Adverse effect of unspecified antidepressants, sequela
3. Circadian rhythm sleep disorder, shift work
In example 1, the comma is used to specify the degree of the disorder, whereas
in example 2, it is used to define the kind of adverse effect. Finally, in example
3, the comma is used to specify the cause of the disorder.
This diverse use of parentheses, square brackets and commas, complicates
labels, penalising matchers’ performance. Thus, we decided to suppress commas
and all content within parentheses and square brackets to avoid this penalisation.
This simplifies labels and reduces irrelevant content. Nonetheless, in the future,
we should investigate less aggressive solutions to reduce matchers penalisation
while taking advantage of the content within parentheses.
Using Domain Lexicon and Grammar for Ontology Matching 9
5 Evaluation
The hypothesis has been evaluated by an experiment in which matchers
with different configurations had to match several descriptions of the two
most important classifications of diseases for mental health: the Diagnostic
and Statistical Manual of Mental Disorders, fifth edition (DSM-5) and the
ICD-10. To evaluate the quality of the matchers, we used as gold standard the
correspondences between both classifications published in DSM-5, where it is
specified to which code in ICD-10 corresponds each description in DSM-5.
The input schemas were a source dataset with 200 entries randomly selected
from DSM-5, and a target dataset with 177 descriptions included in ICD-10,
which are the correspondences of the entries chosen from DSM-5.
The matchers selected were S-Match [14] and LogMap [15]. The main reasons
of choosing these two matchers are their differences to carry out the matching
process, and the diverse BK they use. Whereas the former carries out semantic
matching, the latter is a highly scalable system that has reasoning and diagnosis
capabilities allowing it to detect and repair unsatisfiability on the fly [10].
S-Match uses by default WordNet as BK, so it only includes general knowledge,
whereas LogMap only incorporates by default biomedical knowledge provided by
resources within of the Unified Medical Language System (UMLS). Regarding
grammar, both matchers are limited to address general grammar. While S-Match
includes tokenisation, lemmatisation and the translation of punctuation marks
into logical connectives, LogMap implements string similarity measures, stop
words elimination and word stemming.
The experiments were executed 4 times with each matcher, computing the
standard metrics within the information retrieval community: precision, recall
and f-measure. Firstly, with the vanilla version, which was our baseline in each
case; secondly, with the lexicon extension; thirdly, with the grammar extension,
and finally, with both extensions.
Figure 1 and figure 2 depict the results of the experiments executed in
S-Match and LogMap, respectively. We can see how both matchers, S-Match
and LogMap, improve their performance in terms of f-measure around 20% and
7% respectively. It is also noticeable, that overall both matchers achieve low
results which are caused by the nature of the input labels, which on average are
descriptions with more than 5-6 words, so this results in complex label formulas
and low string similarity values.
Regarding S-Match, the vanilla version only has a general BK and the
matcher is penalised mainly for the way in which it manages commas (each
comma is considered as a disjunctive operator). This caused a huge number
of false positives, which negatively affected precision, but also discovered, as
side effect, a high number of correspondences, resulting in the highest recall. An
example is the label “Mild cognitive impairment, so stated ” which is transformed
into the following label formula:
mild & cognitive state & impairment | state
From this label formula S-Match computes the following node formula:
10 Quesada et al.
Fig. 1. Results of the experiments executed in S-Match.
(mild | state) & (cognitive state | state) & (impairment | state)
That means that if “state” has a relationship with a lemma within any label of
the other ontology, the matcher will output a mapping even if the rest of the
label is not related.
The lexicon extension considerably improves the performance (11%) by
adding health lexicon knowledge, but this extension also avoids some of the
correspondences discovered as side effect, mainly with the inclusion of lexical
entries that were considered as single tokens in the vanilla version and now are
compound tokens, so the recall slightly decreases.
The grammar extension is the one that drastically reduces the number of false
positives mainly with the techniques applied at phrase and character grammar
levels that were employed as a preprocessing step prior to the matching process.
In addition, it also discovers new mappings thank to the derivational morphology
implemented at word grammar level.
The combination of both lexicon and grammar extensions is the configuration
that performs better in terms of f-measure, complementing each other and
improving the baseline around 20%. However, the false positives of both
extensions are also aggregated, being precision slightly penalised.
As for LogMap (see Figure 2), the vanilla version includes biomedical
knowledge by default, resulting in a baseline with a performance over 60%.
The lexicon extension added knowledge coming from SPECIALIST, MeSH
and WordNet, but it was the latter which produced the major impact as it added
domain-independent knowledge contained in the labels. This new knowledge
also produced some false positives, but on average this configuration improved
the baseline around 6.3%. An example of false positive is:“Narcolepsy without
cataplexy but with hypocretin deficiency” ≡ “Narcolepsy with cataplexy”, while
an example of new true positive is: “Acute stress disorder ” ≡ “Acute stress
reaction”.
The grammar extension had a similar effect mainly because it also
incorporated WordNet. In this case, tasks for word and character grammar levels
Using Domain Lexicon and Grammar for Ontology Matching 11
Fig. 2. Results of the experiments executed in LogMap.
had a low impact on LogMap. Nonetheless, phrase level grammar preprocessing
had a significant impact, and the performance improved 6.5% with respect to
the baseline. Examples of new true positives are: “Trichotillomania (hair-pulling
disorder)” ≡ “Trichotillomania”, and “Overweight or obesity” ≡ “Obesity,
unspecified ”.
The combination of both extensions was the configuration that obtained the
best performance, achieving the highest number of true positives discovered. In
this case, the baseline is improved more than 7%.
6 Concluding Remarks
In this paper, we have presented an approach in which matchers can take
advantage of both, domain lexicon and grammar to improve their performance
when matching domain-knowledge resources. After evaluating our approach by
matching some descriptions of mental health disorders included in DSM-5 and
ICD-10 with S-Match and LogMap, we can conclude that our hypothesis is true,
as both matchers improve their f-measure compared with the vanilla version.
It is interesting to highlight how the use of domain lexicon and grammar
affects differently depending on the matcher. Whereas the domain lexicon
extension has the major impact on LogMap, S-Match experiences its major
improvement with the grammar extension. The main reason is that LogMap
now can discover new mappings thank to domain-independent knowledge, and
S-Match has label formulas significantly simplified. This information is useful
in order to optimise efforts in the future, and help to decide whether is more
valuable investing time focusing on integrating domain lexicon or grammar
knowledge into matcher’s KB.
As future work we should explore other factors that may affect matchers
when matching domain-knowledge, such as the impact of each kind of knowledge
represented within knowledge resources according to their levels of specificity.
Moreover, it is interesting to delve into methods to aggregate lexicon and
grammar results in order to optimise matcher’s performance.
12 Quesada et al.
Acknowledgements
This research was partially supported by the European Commission
with the grant agreement No. 607062 (ESSENCE Marie Curie ITN,
http://www.essence-network.com/).
References
1. Amaro, R., Mendes, S.: Towards merging common and technical lexicon wordnets.
In: Proceedings of the 3rd Workshop on Cognitive Aspects of the Lexicon. pp.
147–160 (2012)
2. Annane, A., Bellahsene, Z., Azouaou, F., Jonquet, C.: Yam-bio–results for oaei
2017. In: CEUR Workshop Proceedings (2017)
3. Bella, G., Giunchiglia, F., McNeill, F.: Language and domain aware lightweight
ontology matching. Journal of Web Semantics 43, 1–17 (2017)
4. Bella, G., McNeill, F., Leoni, D., Quesada Real, F.J., Giunchiglia, F.: Diversicon:
Pluggable lexical domain knowledge. Journal on Data Semantics pp. 1–16 (2019)
5. Bella, G., Zamboni, A., Giunchiglia, F.: Domain-based sense disambiguation
in multilingual structured data. In: The Diversity Workshop at the European
Conference on Artificial Intelligence (ECAI) (2016)
6. Bella, G., Elliot, L., Das, S., Pavis, S., Turra, E., Robertson, D., Giunchiglia,
F.: Cross-border medical research using multi-layered and distributed knowledge
(2020)
7. Browne, A.C., McCray, A.T., Srinivasan, S.: The specialist lexicon. National
Library of Medicine Technical Reports pp. 18–21 (2000)
8. Da Silva, J., Revoredo, K., Baião, F., Euzenat, J.: A lin: improving interactive
ontology matching by interactively revising mapping suggestions. The Knowledge
Engineering Review 35 (2020)
9. Dragisic, Z., Ivanova, V., Li, H., Lambrix, P.: Experiences from the anatomy track
in the ontology alignment evaluation initiative. Journal of biomedical semantics
8(1), 56 (2017)
10. Euzenat, J., Shvaiko, P.: Ontology Matching - Second Edition. Springer (2013)
11. Faria, D., Pesquita, C., Santos, E., Palmonari, M., Cruz, I.F., Couto, F.M.:
The agreementmakerlight ontology matching system. In: OTM Confederated
International Conferences” On the Move to Meaningful Internet Systems”. pp.
527–541. Springer (2013)
12. Fellbaum, C.: WordNet. Wiley Online Library (1998)
13. Francopoulo, G.: Lmf iso 24613:2008 (Mar 2008)
14. Giunchiglia, F., Shvaiko, P., Yatskevich, M.: S-match: an algorithm and an
implementation of semantic matching. In: European semantic web symposium.
pp. 61–75. Springer (2004)
15. Jiménez-Ruiz, E., Cuenca Grau, B.: Logmap: Logic-based and scalable ontology
matching. In: International Semantic Web Conference. pp. 273–288. Springer
(2011)
16. Lipscomb, C.E.: Medical subject headings (mesh). Bulletin of the Medical Library
Association 88(3), 265 (2000)
17. Quesada Real, F.J., McNeill, F., Bella, G., Bundy, A.: Improving dynamic
information exchange in emergency response scenarios. In: Proceedings of 14th
International Conference on Information Systems for Crisis Response and
Management (ISCRAM 2017). pp. 824–833 (2017)
18. Quesada Real, F.J., McNeill, F., Bella, G., Bundy, A.: Identifying semantic domains
in emergency scenarios. In: 15th International Conference on Information Systems
for Crisis Response and Management (ISCRAM 2018). pp. 1130–1132 (2018)