Mustafa Jarrar: Lecture Notes on Wordnets

Birzeit University, 2025

Version 6

‫محـــــر كبحـــــ ث لل مع اجـــــ م العربيـــــ ة‬

ّ

Natural Language Processing

Wordnets

Mustafa Jarrar
Birzeit University

Jarrar © 2025 1
 Watch this lecture
and download the slides

Course Page: http://www.jarrar.info/courses/NLP/

More Online Courses at: http://www.jarrar.info

Keywords:
Arabic, Arabic NLP, NLP, Natural Language Processing, Thesauri, linguistic ontology, Arabic Ontology, Wordnet, Arabic WordNet, EURO WordNet, Global WordNet, Lexical Semantics, Word sense
disambiguation, mental lexicon, Synset, Concept, Gloss, Polysemy, Semantic Relations, Hyponymy, Meronymy, Antonymy, Ontology, ،‫ مفهوم‬،‫متادفات‬ ‫ ر‬،‫ معجم ذهن‬،‫ حوسبة الداللة‬،‫ وردنت‬،‫شبكة المفردات‬
‫ ر‬،‫ تعدد اللغات‬،‫ أنطولوجيا لغوية‬،‫ االنطولوجيا العربية‬،‫ حوسبة اللغة‬،‫ مكت‬،‫تعريف‬ ‫ي‬
‫كل‬-‫ عالقات جزء‬،‫ان‬
‫ي‬ ‫المع‬ ‫تصنيف‬ ،‫التضاد‬ ،‫المعان‬
‫ي‬ ‫تعدد‬ ،‫اللغوي‬ ‫ادف‬
‫الت‬

Jarrar © 2025 2
 Mustafa Jarrar: Lecture Notes on Introduction to Wordnets
Birzeit University, 2025

Natural Language Processing

Introduction to Wordnets
In this lecture:

 Part 1: What and why Thesauri

 Part 2: WordNet

 Part 3: EuroWordnet
 Part 4: Global Wordnet
 Part 5: Discussion
 Part 6: Practice

Jarrar © 2025 3
 Reading

Everything in these slides + everything I say

[MBC93] George A. Miller, Richard Beckwith, Christiane Fellbaum, Derek Gross,

and Katherine Miller: Introduction to WordNet: An On-line Lexical
Database. International Journal of Lexicography, Vol. 3, Nr. 4. Pages 235-
244. (1990) http://wordnetcode.princeton.edu/5papers.pdf

[J21] Mustafa Jarrar: The Arabic Ontology - An Arabic Wordnet with

Ontologically Clean Content. Applied Ontology Journal. IOS, 2019.
https://www.jarrar.info/publications/J21.pdf

Jarrar © 2025 4
 Why Lexical Semantic Resources?

The importance of lexical semantic resources )such as thesauri,

wordnets, linguistic ontologies) is increasing in many application
areas, such as:
• Word sense disambiguation
• Smarter Information search and retrieval
• Multilingual semantic web and knowledge graphs
• NLP tasks and applications (classification/ summarization/translation)
• Data integration
• Multilingual big data
• among many others.
Jarrar © 2025 5
 Thesaurus (‫ )مكت‬as a source of semantics
A list of words classified as near-synonyms.

Examples:
Thesaurus of English words and phrases ‫العرب المعارص‬ ‫زز‬
‫المكن‬
‫ز‬ ‫ز‬ ‫ي‬
‫محمود إسماعيل ز‬
Peter Mark Roget · 1883 1993 ‫مصطف أحمد سليمان‬ ،‫مصطف عبدالعزيز‬ ‫ ناصيف‬، ‫صين‬
‫ي‬

Jarrar © 2025 6
 Thesaurus (‫ )مكت‬as a source of semantics

A list of words classified as near-synonyms;

or

it can be seen as pairs of terms connected through “RelatedTo” and/or a

“Broader/Narrow” relations.

However, such relations are semantically-poor and imprecise relationships

between words and not sufficient for most IT-based applications.

 From thesaurus to wordnet

Jarrar © 2025 7
 Mustafa Jarrar: Lecture Notes on Introduction to Wordnets
Birzeit University, 2025

Natural Language Processing

Introduction to Wordnets
In this lecture:
 Part 1: What and why Thesauri

 Part 2: WordNet
 Part 3: EuroWordnet
 Part 4: Global Wordnet
 Part 5: Discussion
 Part 6: Practice

Jarrar © 2025 8
 What is WordNet?
‫شبكة مفردات‬

• In 1985 a group of psychologists and linguists at Princeton University

started to develop a “mental lexicon” ‫ذهن‬‫ معجم ز‬.
‫ي‬
• You may also call it: electronic dictionary, mental dictionary, semantic Network,
hyperdimensional thesaurus, lexicographic database, (recently called linguistic
ontology). etc.
• Includes most frequent words (nouns, adjectives, adverbs, verbs).
• Organized by meaning: words in close proximity are semantically similar.
• Can be used by humans and machines.
• Human users and computers can browse WordNet and find words that are
meaningfully related to their queries.
• Available online, for downloading! http://wordnet.princeton.edu
Jarrar © 2025 9
 Basic Concepts
• English words are grouped into sets of synonyms called a Synset.
• Each synset is given a unique SynsetID.
• Each synset signify that a Concept exist – expressing a meaning.
• Each word form-meaning pair is unique: Sense.
• Each synset is described by a gloss (examples of contexts).
03410635 07955878

{Furniture, Piece of furniture , {Categorization,

Article of furniture} Classification}
A group of people or things
Furnishings that make a room….
arranged…
08283156

03018908
{Table, Tabular Array}
A set of data arranged in rows
{Bureau, Dresser, and columns
Chest of Drawers,} 04615793
Furniture with drawers for
keeping clothes {work table} 06501650

A table designed… {Contents,

TableOfContents}
A list of divisions…
Jarrar © 2025 10
 WordNet: Polysemy
• A word that appears in n synsets is n-fold polysemous.
• For example: “Table” here is two-fold polysemous

{Furniture, Piece of furniture

{Stream} {Arrangement}
, Article of furniture}
An orderly grouping (of things or…
Furnishings that make a room…. A natural body of
running water…

{Bureau, Dresser, {Array} {Categorization,

{Table} Classification}
Chest of Drawers,} A piece of furniture {River} An orderly arrangement
A group of people or
Furniture with drawers for having a smooth… A large natural things arranged…
keeping clothes stream of ...
{Table, Tabular Array}
{Desk} A set of data arranged in rows {Matrix}
A piece of furniture {Nile} and columns
A rectangular array
with a writing surface… of quantities …
The world's
longest..
{Booth} {Calendar} {Contents,
A table (in a restaurant or
{work table} A tabular array TableOfContents} {Periodic Table}
a tabular arrangement
of the days.. A list of divisions…
bar) surrounded by two… A table designed… of the chemical elem…
Jarrar © 2025 11
 WordNet: Glosses
A short gloss is provided for each sysnet.
Glosses are examples of contexts for many word-sense pairs, telling
us how words with specific senses are being used in context.

{Furniture, Piece of furniture

{Stream} {Arrangement}
, Article of furniture}
An orderly grouping )of things or…
Furnishings that make a room…. A natural body of
running water…

{Bureau, Dresser, {Array} {Categorization,

{Table} Classification}
Chest of Drawers,} A piece of furniture {River} An orderly arrangement
A group of people or
Furniture with drawers for having a smooth… A large natural things arranged…
keeping clothes stream of ...
{Table, Tabular Array}
{Desk} A set of data arranged in rows {Matrix}
A piece of furniture {Nile} and columns
A rectangular array
with a writing surface… of quantities …
The world's
longest..
{Booth} {Calendar} {Contents,
A table (in a restaurant or
{work table} A tabular array TableOfContents} {Periodic Table}
a tabular arrangement
of the days.. A list of divisions…
bar) surrounded by two… A table designed… of the chemical elem…
Jarrar © 2025 12
 WordNet: Glosses

155 287 word forms, groups into

117 659 synsets WordForms Synsets
noun 117,798 82,115
{Furniture, Piece of furniture
verb 11,529 13,767
{Stream} {Arrangement}
, Article of furniture}
Furnishings that make a room….
adjective
A natural body of
21,479
An orderly grouping (of things or… 18,156
running water…

{Bureau, Dresser, adverb {Array} 4,481{Categorization,

3,621
{Table} Classification}
Chest of Drawers,} A piece of furniture {River}
Total
An orderly arrangement
155,287Athings
group117,659
of people or
Furniture with drawers for having a smooth… A large natural arranged…
keeping clothes stream of ...
{Table, Tabular Array}
{Desk} A set of data arranged in rows {Matrix}
A piece of furniture {Nile} and columns
A rectangular array
with a writing surface… of quantities …
The world's
longest..
{Booth} {Calendar} {Contents,
A table (in a restaurant or
{work table} A tabular array TableOfContents} {Periodic Table}
a tabular arrangement
of the days.. A list of divisions…
bar) surrounded by two… A table designed… of the chemical elem…
Jarrar © 2025 13
 WordNet Semantic Relations
Synsets are interconnected with semantic relations, forming a large
semantic network (graph). Such Relations are:
• Hyponymy, also called “Is a” relation, or sub/superordinate.
• Meronymy, also called “part of” relation

{Furniture, Piece of furniture

{Container} , Article of furniture} {Stream} {Arrangement}
Any object that can An orderly grouping (of things or…
Furnishings that make a room…. A natural body of
be used .. running water…

{Bureau, Dresser, {Array} {Categorization,

{Table} Classification}
{Drawer} Chest of Drawers,} {River} An orderly arrangement
A piece of furniture A group of people or
A boxlike container in.. Furniture with drawers for having a smooth… A large natural things arranged…
keeping clothes stream of ...
{Table, Tabular Array}
{Desk} A set of data arranged in rows {Matrix}
{shelf} A piece of furniture {Nile} and columns
A rectangular array
with a writing surface… of quantities …
A support that consists… The world's
longest..

{Support} {Booth} {Calendar} {Contents,

A table (in a restaurant or
{work table} A tabular array TableOfContents} {Periodic Table}
a tabular arrangement
Any device that bears.. of the days.. A list of divisions…
bar) surrounded by two… A table designed… of the chemical elem…
Jarrar © 2025 14
 WordNet Relations: Hyponymy
• A synset {x, x′, . . .} is hyponym of the synset {y, y′, . . .} if native English
speakers accept sentences like x is a (kind of) y. E. g., Table/Tabular Array
is a kind of Array, Array is a kind of Arrangement,…
• Hyponymy is transitive and asymmetrical. So as Hyponymy generates a hierarchical
semantic structure, a hyponym inherits all the features of the more generic concept and
adds at least one feature that distinguishes it from its superordinate.
{Furniture, Piece of furniture
{Stream} {Arrangement}
, Article of furniture}
An orderly grouping (of things or…
Furnishings that make a room…. A natural body of
running water…

{Bureau, Dresser, {Array} {Categorization,

{Table} Classification}
Chest of Drawers,} A piece of furniture {River} An orderly arrangement
A group of people or
Furniture with drawers for having a smooth… A large natural things arranged…
keeping clothes stream of ...
{Table, Tabular Array}
{Desk} A set of data arranged in rows {Matrix}
A piece of furniture {Nile} and columns
A rectangular array
with a writing surface… of quantities …
The world's
longest..
{Booth} {Calendar} {Contents,
A table (in a restaurant or
{work table} A tabular array TableOfContents} {Periodic Table}
a tabular arrangement
of the days.. A list of divisions…
bar) surrounded by two… A table designed… of the chemical elem…
Jarrar © 2025 15
 WordNet Relations: Hyponymy
• A synset {x, x′, . . .} is hyponym of the synset {y, y′, . . .} if native English
speakers accept sentences like x is a (kind of) y. E. g., Table/Tabular Array
is a kind of Array, Array is a kind of Arrangement,…
• Hyponymy is transitive and asymmetrical. So as Hyponymy generates a hierarchical
semantic structure, a hyponym inherits all the features of the more generic concept and
adds at least one feature that distinguishes it from its superordinate.
Top Level Nouns (25 unique beginners)
{act, action, activity} {natural object }
{animal, fauna} {natural phenomenon }
{artifact } {person, human being}
{attribute, property } {plant, flora}
{body, corpus} {possession}
The WordNet hierarchy is {cognition, knowledge} {process}
about 16 levels {communication} {quantity, amount}
{event, happening} {relation }
{feeling, emotion} {shape}
{food} {state, condition}
{group, collection} {substance}
{location, place } {time}
{motive} Jarrar © 2025 16
 WordNet Relations: Meronymy
• A synset {x, x′, . . .} is meronym of the synset {y, y′, . . .} if native English
speakers accept sentences like y has an x (as a part) or An x is a part of y.
E. g., Finger is part of Hand , Hand is part of Arm, Arm is part of Body.
• Meronymy is transitive )with qualification) and asymmetrical relations, and
forms a part hierarchy.
• Synsets may have multiple hypernyms

{Furniture, Piece of furniture

{Container} , Article of furniture} {Stream} {Arrangement}
Any object that can An orderly grouping )of things or…
Furnishings that make a room…. A natural body of
be used .. running water…

{Bureau, Dresser, {Array} {Categorization,

{Table} Classification}
{Drawer} Chest of Drawers,} {River} An orderly arrangement
A piece of furniture A group of people or
A boxlike container in.. Furniture with drawers for having a smooth… A large natural things arranged…
keeping clothes stream of ...
{Table, Tabular Array}
{Desk} A set of data arranged in rows {Matrix}
{shelf} A piece of furniture {Nile} and columns
A rectangular array
with a writing surface… of quantities …
A support that consists… The world's
longest..

{Support} {Booth} {Calendar} {Contents,

A table (in a restaurant or
{work table} A tabular array TableOfContents} {Periodic Table}
a tabular arrangement
Any device that bears.. of the days.. A list of divisions…
bar) surrounded by two… A table designed… of the chemical elem…
Jarrar © 2025 17
 Exercise

Find the hyponyms and meronyms of this synset

{car, auto, automobile, machine, motorcar}

Jarrar © 2025 18
 WordNet Relations: Another Example
[Vossen]

Hyponymy and meronymy relations are:

{conveyance, transport}
• transitive
• directed
{vehicle}
meronyms
{motor vehicle, automotive vehicle} {car mirror} {armrest}
hyper(o)nym
{car door} {doorlock}

{bumper} {hinge,
{car, auto, automobile, machine, motorcar}
flexible
hyponym {car window} joint}

{cruiser, squad car, patrol car, {cab, taxi, hack, taxicab}

police car, prowl car}
Jarrar © 2025 19
 WordNet Relations: Antonymy
• The antonym of a word x is sometimes not-x, but not always. For example, rich and
poor are antonyms, but to say that someone is not rich does not imply that they must be poor;
many people consider themselves neither rich nor poor.
• Antonymy, which seems to be a simple symmetric relation, is actually quite complex,
yet speakers of English have little difficulty recognizing antonyms when they see them. For example, the
meanings {rise, ascend } and {fall, descend} may be conceptual opposites, but they are not antonyms; [rise/fall] are
antonyms and so are [ascend/descend], but most people hesitate and look thoughtful when asked if rise and
descend, or ascend and fall, are antonyms
• Antonymy is a lexical relation between word forms, not a semantic relation between word meanings.
Or, some call it semantic relations between words [MPC93].
{Rise, Uprise, Come up,
{Hot} {Cold} Go up, Move up, Lift} {Fall, Come Down, Go
Used of physical Having a low or Move upward
heat; having.. inadequate.. Down, Descend}
{New} {Worn} {Ascend, Move up, Rise} Move downward and lower, but not
necessarily all the way
Unaffected by use Affected by wear; Move to a better position in life …
or exposure damaged by …
{Ascend, Go up}
{New} {Old} Travel up
{Set, Go down, Go Under}
Not of long
duration; having..
Of long duration {Ascend, Come (astronomy) disappear beyond the horizon
{Old} up, Rise, Uprise}
{Young, Immature} (astronomy) come up, of
having lived
in an early period of life… for a relatively Jarrar © 2025
celestial bodies 20
 WordWeb
http://wordweb.info/free/

A nice and intuitive

interface for WordNet

Jarrar © 2025 21
 Other WordNet Relations

• Although the main interest of WordNet was on specifying semantic relations

but other lexical/morphological relations between word forms were added.

• For example: stems, singular-plural, verb tenses, etc.

Jarrar © 2025 22
 Is WordNet a Thesaurus?
Yes:
• it groups together meaningfully related words

and more:

• WordNet provides more accurate relations,

Thesaurus contains only related-to.

• Related words are linked to specific concepts (disambiguated),

Thesaurus is a “bag of words”

 Wordnets are next generation Thesauri

Jarrar © 2025 23
 Is WordNet an Ontology?

Ontological Precision:
WordNet: based on what native speakers agree roughly.
Ontology: based on Scientific and philosophical findings.

Classification:
WordNet: based on what native speakers agree roughly (Student IsA person)
Ontology: based on strict formal methodologies (student IsA role)

Formal Specification:
WordNet: logically vague (and, contains concepts without instance)
Ontology: strictly formal (every concepts can be instantiated)

Jarrar © 2025 24
 Examples of ontological matters in WordNet
Examples problems in WordNet, which limited its use in IT applications:
• (Nile Is-a River) is formal mistake, Nile is an instance of River.
• (Student Is-a Person) is ontologically incorrect; Student is a Role
• (Italy Is-a Land5) and (Italy Is-a Nation) is ontologically incorrect. cannot
subsume the two disjoint concepts, land5 and nation, at the same time.

• (Reflate2 Is-a Inflate3) (Inflate3 Is-a Change1) and (Reflate2 Is-a Change1)
is meaningless, this is an implied relation.
• (Restrain1 Is-a Inhibit4) and (Inhibit4 Is-a Restrain1) is a cycle.
• (Islamic Month Is-a Month) is inaccurate, Month = twelve divisions of the
Gregorian year (i.e., 30.43 days); but Islamic month is 29.53 days.
• Moring and Evening Stars as different stars is inaccurate. They are the
same instance (i.e., Venus) that people see at different occasions.
 From thesaurus to wordnet to linguistic ontology
Jarrar © 2025 25
 Mustafa Jarrar: Lecture Notes on Introduction to Wordnets
Birzeit University, 2025

Natural Language Processing

Introduction to Wordnets
In this lecture:
 Part 1: What and why Thesauri
 Part 2: What is WordNet

 Part 3: EuroWordnet
 Part 4: Global Wordnet
 Part 5: Discussion
 Part 6: Practice

Jarrar © 2025 26
 EURO WordNet [Vossen]

• The development of a multilingual database with WordNets for

several European languages.
• Funded by the European Commission, DG XIII, LE2-4003 and LE4-8328
• March 1996 - September 1999 (2.5 Million EURO)
http://www.hum.uva.nl/~ewn
http://www.illc.uva.nl/EuroWordNet/finalresults-ewn.html

• Languages covered:
EuroWordNet-1 (LE2-4003): English, Dutch, Spanish, Italian
EuroWordNet-2 (LE4-8328): German, French, Czech, Estonian.

• Size of vocabulary:
EuroWordNet-1: 30,000 concepts - 50,000 word meanings.
EuroWordNet-2: 15,000 concepts- 25,000 word meaning.

• Type of vocabulary:
the most frequent words of the languages
all concepts needed to relate more specific concepts.
Jarrar © 2025 27
 EURO WordNet Model
[Vossen]

Domains Ontology
move bewegen
go Traffic 2OrderEntity gaan

III Air Road` Location Dynamic III

ride drive rijden berijden

III III
II
Lexical Items Table I I Lexical Items Table

II Lexical Items Table

Lexical Items Table ILI-record
{drive}
III III
cabalgar II
conducir guidare cavalcare
jinetear
Inter-Lingual-Index II
III III

mover I = Language Independent link andare

transitar II = Link from Language Specific muoversi
to Inter lingual Index
III = Language Dependent Link
Jarrar © 2025 28
 The Multilingual Design
[Vossen]

• Inter-Lingual-Index: unstructured fund of concepts to provide an

efficient mapping across the languages;

• Index-records are mainly based on WordNet synsets and consist of

synonyms, glosses and source references;

• Various types of complex equivalence relations are distinguished;

• Equivalence relations from synsets to index records: not on a word-to-word

basis;

• Indirect matching of synsets linked to the same index items;

Jarrar © 2025 29
 EURO WordNet Model
[Vossen]

• WordNets are unique language-specific structures:

 same organizational principles: synset structure and same set of
semantic relations.
 different lexicalizations
 differences in synonymy and homonymy:
"decoration" in English versus "versiersel/versiering" in Dutch
"bank" in English (money/river) versus "bank" in Dutch
(money/furniture)

•BUT also different relations for similar synsets

Jarrar © 2025 30
Some Downsides of the EuroWordNet Model
[Vossen]

• Construction is not done uniformly

• Coverage differs

• Not all wordnets can communicate with one another, i.e. linked
to different versions of English wordnet

• Proprietary rights restrict free access and usage

• A lot of semantics is duplicated

• Complex and obscure equivalence relations due to linguistic

differences between English and other languages

Jarrar © 2025 31
 Mustafa Jarrar: Lecture Notes on Introduction to Wordnets
Birzeit University, 2025

Natural Language Processing

Introduction to Wordnets
In this lecture:
 Part 1: What and why Thesauri
 Part 2: What is WordNet
 Part 3: EuroWordnet

 Part 4: Global Wordnet

 Part 5: Discussion
 Part 6: Practice

Jarrar © 2025 32
From EuroWordNet to Global WordNet

http://www.globalwordnet.org

Jarrar © 2025 33
 From EuroWordNet to Global WordNet
[Vossen]

• EuroWordNet ended in 1999

• Global Wordnet Association was founded in 2000 to maintain the

framework: http://www.globalwordnet.org
• Currently, wordnets exist for more than 80 languages, including:
Albanian, Arabic, Bantu, Basque, Chinese, Bulgarian, Estonian, Hebrew, Icelandic,
Japanese, Kannada, Korean, Latvian, Nepali, Persian, Romanian, Sanskrit, Tamil,
Thai, Turkish, Zulu...

• Many languages are genetically and typologically unrelated

 The Arabic WordNet extension was not successful.

Jarrar © 2025 34
 Arabic WordNet
• Literal and ad hoc translation for 10000 English synsets, and
never extended!

• The 10000 synsets were selected as the following:

• A set of concepts (called base concepts) were selected as they exist in 12

languages (in EuroWordNet and BalkeNet, (Elkateb et al 2006), thus they
are assumed to also exist in Arabic.

• The base concepts were then extended mostly downwards with more
specific concepts, and upwards with more general concepts, to improve
the maximal connectivity of those base concepts.

• Some new synsets were added – mostly names of cities

Download: https://sourceforge.net/projects/awnbrowser
Jarrar © 2025 35
 Mustafa Jarrar: Lecture Notes on Introduction to Wordnets
Birzeit University, 2025

Natural Language Processing

Introduction to Wordnets
In this lecture:
 Part 1: What and why Thesauri
 Part 2: What is WordNet
 Part 3: EuroWordnet
 Part 4: Global Wordnet

 Part 5: Discussion
 Part 6: Practice

Jarrar © 2025 36
 Mustafa Jarrar: Lecture Notes on Introduction to Wordnets
Birzeit University, 2025

Natural Language Processing

Introduction to Wordnets
In this lecture:
 Part 1: What and why Thesauri
 Part 2: What is WordNet
 Part 3: EuroWordnet
 Part 4: Global Wordnet
 Part 5: Discussion

 Part 6: Practice

Jarrar © 2025 37
 References
[Vossen] Piek Vossen, From WordNet,toEuroWordNet,to the Global Wordnet Grid. Lecture notes
[MBC93] George A. Miller, Richard Beckwith, Christiane Fellbaum, Derek Gross, and Katherine Miller: Introduction to WordNet: An On-line Lexical Database. International Journal of Lexicography, Vol. 3, Nr. 4.
Pages 235-244. (1990)
[J21] Mustafa Jarrar: The Arabic Ontology - An Arabic Wordnet with Ontologically Clean Content. Applied Ontology Journal, 16:1, 1-26. IOS Press. 2021
1. Mustafa Jarrar, Tymaa Hammouda: Qabas: An Open-Source Arabic Lexicographic Database. In Proceedings of LREC-COLING 2024, pages 13363–13370, Torino, Italia. ELRA and ICCL.
2. Mustafa Jarrar, Sanad Malaysha, Tymaa Hammouda, Mohammed Khalilia: SALMA: Arabic Sense-Annotated Corpus and WSD Benchmarks. Proceedings the 1st ArabicNLP, Part of the ACL 2023. ACL.
3. Sana Ghanem, Mustafa Jarrar, Radi Jarrar, Ibrahim Bounhas: A Benchmark and Scoring Algorithm for Enriching Arabic Synonyms. In Proceedings of GWC2023, (pp.274-283). Spain, 2023
4. Sanad Malaysha, Mustafa Jarrar, Mohammed Khalilia: Context-Gloss Augmentation for Improving Arabic Target Sense Verification. In Proceedings of GWC2023, (pp.274-283). Spain, 2023
5. Moustafa Al-Hajj, Mustafa Jarrar: ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSD. In Proceedings of the International Conference on Recent Advances in Natural Language Processing
(RANLP 2021). PP 40--48, 2021
6. Moustafa Al-Hajj, Mustafa Jarrar: LU-BZU at SemEval-2021 Task 2: Word2Vec and Lemma2Vec performance in Arabic Word-in-Context disambiguation. In Proceedings of the Fifteenth Workshop on
Semantic Evaluation (SemEval2021) Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation (MCL-WiC). PP 748--755, Association for Computational Linguistics. 2021
7. Mustafa Jarrar, Eman Karajah, Muhammad Khalifa, Khaled Shaalan: Extracting Synonyms from Bilingual Dictionaries. The 11th International Global Wordnet Conference (GWC2021), Global Wordnet
Association. (pp. 215-222). Pretoria, South Africa, 2021
8. Mustafa Jarrar, Hamzeh Amayreh: An Arabic-Multilingual Database with a Lexicographic Search Engine. The 24th International Conference on Applications of Natural Language to Information Systems
(NLDB 2019). Pages(234-246). LNCS 11608, Springer. 2019
9. Mustafa Jarrar, Hamzeh Amayreh, John P. McCrae: Representing Arabic Lexicons in Lemon - a Preliminary Study. The 2nd Conference on Language, Data and Knowledge (LDK 2019). Pages(29-33). CEUR,
Volume 2402. ISSN:1613-0073. Leipzig, Germany. 2019
10. Diana Alhafi, Anton Deik, Mustafa Jarrar: Usability Evaluation of Lexicographic e-Services. The 16th IEEE/ACS International Conference on Computer Systems and Applications (AICCSA). Pages(1-7). IEEE. Abu
Dhabi, UAE. 2019
11. Mustafa Jarrar, Fadi Zaraket, Rami Asia, Hamzeh Amayreh: Diacritic-Based Matching of Arabic Words. ACM Asian and Low-Resource Language Information Processing. Volume 18, No 2, Pages(10:1-10:21),
ACM, ISSN:2375-4699. December, 2018
12. Mustafa Jarrar, Werner Ceusters: Classifying Processes and Basic Formal Ontology. Proceedings of the 8th International Conference on Biomedical Ontology (ICBO 2017), Newcastle, UK. 2017
13. Mustafa Jarrar: Building a Formal Arabic Ontology (Invited Paper). In proceedings of the Experts Meeting on Arabic Ontologies and Semantic Networks. Alecso, Arab League. Tunis, July 26-28, 2011.
14. Mustafa Jarrar: Towards the notion of gloss, and the adoption of linguistic resources in formal ontology engineering. In proceedings of the 15th International World Wide Web Conference (WWW2006).
Edinburgh, Scotland. Pages 497-503. ACM Press. ISBN: 1595933239. May 2006.
15. Mustafa Jarrar, Anton Deik, Bilal Faraj: Ontology-based Data and Process Governance Framework -The Case of e-Government Interoperability in Palestine. Proceedings of the IFIP International Symposium
on Data-Driven Process Discovery and Analysis (SIMPDA’11). Pages(83-98). 2011.
16. Mustafa Jarrar and Robert Meersman: Ontology Engineering -The DOGMA Approach. Book Chapter in "Advances in Web Semantics I". Chapter 3. Pages 7-34. LNCS 4891, Springer. (2008).
17. Mustafa Jarrar: Tutorial on Arabic Ontology Engineering. The ACS/IEEE International Conference on Computer Systems and Applications. Tunis, 2017
18. Mustafa Jarrar, Maria Keet, and Paolo Dongilli: Multilingual verbalization of ORM conceptual models and axiomatized ontologies . Technical report. STARLab, Vrije Universiteit Brussel, February 2006.
19. Mustafa Jarrar: Mapping ORM into the SHOIN/OWL Description Logic- Towards a Methodological and Expressive Graphical Notation for Ontology Engineering . In OTM 2007 workshops: Proceedings of the
International Workshop on Object-Role Modeling (ORM'07). Pages (729-741), LNCS 4805, Springer. ISBN: 9783540768890. Portogal. November, 2007

Jarrar © 2025 38