[DHSI] Workshop on Generative AI and Knowledge Graphs (GenAIK) co-located with COLING 2025

--===============4771275518343244041==
Content-Type: multipart/alternative; boundary="00000000000078dd2b06254f51d2"

--00000000000078dd2b06254f51d2
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

=EF=BB=BF------------------------------------------------------------------=
---------------
Workshop on Generative AI and Knowledge Graphs (GenAIK),
19 January 2025,  Abu Dhabi, UAE
Web: https://genetasefa.github.io/GenAIK2025/
X: @GenAIK25
LinkedIn: https://www.linkedin.com/groups/9868047
Mastodon: https://sigmoid.social/@GenAIK
---------------------------------------------------------------------------=
------
In conjunction with COLING 2025, January 19-24
---------------------------------------------------------------------------=
------
Workshop Overview
---------------------------------------------------------------------------=
------
Generative Artificial Intelligence (GenAI) is a branch of artificial
intelligence capable of creating seemingly new, meaningful content,
including text, images, and audio. It utilizes deep learning models, such
as Large Language Models (LLMs), to recognize and replicate data patterns,
enabling the generation of human-like content. Notable families of LLMs
include GPT (GPT-3.5, GPT-3.5 Turbo, and GPT-4), LLaMA (LLaMA and LLaMA-2),
and Mistral (Mistral and Mixtral). GPT, which stands for Generative
Pretrained Transformer, is especially popular for text generation and is
widely used in applications like ChatGPT. GenAI has taken the world by
storm and revolutionized various industries, including healthcare, finance,
and entertainment. However, GenAI models have several limitations,
including biases from training data, generating factually incorrect
information, and difficulty in understanding complex content. Additionally,
their performance can vary based on domain specificity.


In recent times, Knowledge Graphs (KGs) have attracted considerable
attention for their ability to represent structured and interconnected
information, and adopted by many companies in various domains. KGs
represent knowledge by depicting relationships between entities, known as
facts, usually based on formal ontological models. Consequently, they
enable accuracy, decisiveness, interpretability, domain-specific knowledge,
and evolving knowledge in various AI applications. The intersection between
GenAI and KG has ignited significant interest and innovation in Natural
Language Processing (NLP). For instance, by integrating LLMs with KGs
during pre-training and inference, external knowledge can be incorporated
for enhancing the model=E2=80=99s capabilities and improving interpretabili=
ty. When
integrated, they offer a robust approach to problem solving in diverse
areas such as information enrichment, representation learning,
conversational AI, cross-domain AI transfer, bias, content generation, and
semantic understanding. This workshop aims at reinforcing the relationships
between Deep Learning, Knowledge Graphs, and NLP communities and foster
interdisciplinary research in the area of GenAI.
---------------------------------------------------------------------------=
------
Topics of Interest
---------------------------------------------------------------------------=
------
* Enhancing KG construction and completion with GenAI
   * Multimodal KG generation
   * Text-to-KG using LLMs
   * Multilingual KGs
* GenAI for KG embeddings
* GenAI for Temporal KGs
* Dialogue systems enhanced by KG and GenAI
* Cross-domain knowledge transfer with GenAI
* Bias mitigation using KGs in GenAI
* Explainability with KGs and GenAI
* Natural language querying of KGs via GenAI
* NLP tasks using KGs and GenAI
* Prompt Engineering using KGs
* GenAI for Ontology learning and schema induction in KGs
* Hybrid QA systems combining KGs and GenAI
* Recommendation systems and KGs with GenAI
* Creating benchmark datasets relevant for tasks combining KGs and GenAI
* Real-world applications on scholarly data, biomedical domain, etc.
* Knowledge Graph Alignment
* Applying to real-world scenarios
---------------------------------------------------------------------------=
---------
Important Dates
---------------------------------------------------------------------------=
---------
- Submission deadline: 5 November 2024
- Notification of Acceptance: 5 December 2024
- Camera-ready paper due: 13 December 2024
- COLING2025 Workshop day: 19 January 2025
---------------------------------------------------------------------------=
---------
Submissions
---------------------------------------------------------------------------=
---------
Full research papers (6-8 pages)
Short research papers (4-6 pages)
Position papers (2 pages)


These page limits only apply to the main body of the paper. At the end of
the paper (after the conclusions but before the references) papers need to
include a mandatory section discussing the limitations of the work and,
optionally, a section discussing ethical considerations. Papers can include
unlimited pages of references and an unlimited appendix.


Papers must follow the two-column format of *ACL conferences, using the
official templates (
https://www.overleaf.com/latex/templates/association-for-computational-ling=
uistics-acl-conference/jvxskxpnznfj/).
The templates are available for download as style files and formatting
guidelines. Submissions that do not adhere to the specified styles,
including paper size, font size restrictions, and margin width, will be
desk-rejected. Submissions are open to all and must be anonymous, adhering
to COLING 2025's double-blind submission and reproducibility guidelines.
All accepted papers  (after double-blind review of at least 3 experts) will
appear in the workshop proceedings that will be published in ACL Anthology.


At least one of the authors of the accepted papers must register for the
workshop to be included into the workshop proceedings. The workshop will be
a 100% in-person 1-day event at COLING 2025.


Submissions must be made using the START portal:
https://softconf.com/coling2025/GenAIK25/


---------------------------------------------------------------------------=
------
Sponsors
---------------------------------------------------------------------------=
------
NFDI4DataScience (NFDI4DS - https://www.nfdi4datascience.de/) is a national
research data infrastructure for Data Science and AI project. The
overarching objective of the project is the development, establishment, and
sustainment of a national research data infrastructure (NFDI) for the Data
Science and Artificial Intelligence community in Germany. The vision of
NFDI4DS is to support all steps of the complex and interdisciplinary
research data lifecycle, including collecting/creating, processing,
analyzing, publishing, archiving, and reusing resources in Data Science and
Artificial Intelligence. NFDI4ds is offering a total of =E2=82=AC2000 in tr=
avel
grants (=E2=82=AC1000 each) to two selected students who will attend and pr=
esent
their work at GenAIK 2025! To be considered, submit your paper to the
workshop, and if your paper is accepted, you=E2=80=99ll be eligible for a c=
hance to
receive one of the two grants.

---------------------------------------------------------------------------=
------
Organization
---------------------------------------------------------------------------=
------
- Genet Asefa Gesese
<https://www.fiz-karlsruhe.de/en/forschung/lebenslauf-und-publikationen-dr-=
ing-genet-asefa-gesese>,
FIZ Karlsruhe, KIT, Germany
- Harald Sack
<https://www.fiz-karlsruhe.de/de/bereiche/lebenslauf-prof-dr-harald-sack>,
FIZ Karlsruhe, KIT, Germany
- Heiko Paulheim
<https://www.uni-mannheim.de/dws/people/professors/prof-dr-heiko-paulheim/>=
,
University of Mannheim, Germany
- Albert Mero=C3=B1o-Pe=C3=B1uela <https://www.albertmeronyo.org/>, King=E2=
=80=99s College
London, UK
- Lihu Chen <https://chenlihu.com/>, Imperial College London, UK

If you have published in ACL conferences previously, and are interested to
be part of the program committee of GenAIK2025, please fill in this form.

--=20
*Dr.-Ing. **Genet Asefa Gesese*
Head of Machine Learning Department (Abteilungsleitung Maschinelles Lernen)
FIZ Karlsruhe =E2=80=93 Leibniz Institute for Information Infrastructure
( *https://www.fiz-karlsruhe.de/en/bereiche/lebenslauf-und-publikationen-dr=
-ing-genet-asefa-gesese
<https://www.fiz-karlsruhe.de/en/bereiche/lebenslauf-und-publikationen-dr-i=
ng-genet-asefa-gesese>*
 )
AND
Karlsruhe Institute of Technology (KIT)
*( https://www.aifb.kit.edu/web/Genet_Asefa_Gesese/en
<https://www.aifb.kit.edu/web/Genet_Asefa_Gesese/en> )*

--00000000000078dd2b06254f51d2
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr"><div dir=3D"ltr">=EF=BB=BF--------------------------------=
-------------------------------------------------<br>Workshop on Generative=
 AI and Knowledge Graphs (GenAIK),<br>19 January 2025, =C2=A0Abu Dhabi, UAE=
<br>Web: <a href=3D"https://genetasefa.github.io/GenAIK2025/" target=3D"_bl=
ank">https://genetasefa.github.io/GenAIK2025/</a>=C2=A0 =C2=A0=C2=A0<br>X: =
@GenAIK25<br>LinkedIn: <a href=3D"https://www.linkedin.com/groups/9868047" =
target=3D"_blank">https://www.linkedin.com/groups/9868047</a> <br>Mastodon:=
 <a href=3D"https://sigmoid.social/@GenAIK" target=3D"_blank">https://sigmo=
id.social/@GenAIK</a> <br>-------------------------------------------------=
--------------------------------<br>In conjunction with COLING 2025, Januar=
y 19-24<br>----------------------------------------------------------------=
-----------------<br>Workshop Overview<br>---------------------------------=
------------------------------------------------<br>Generative Artificial I=
ntelligence (GenAI) is a branch of artificial intelligence capable of creat=
ing seemingly new, meaningful content, including text, images, and audio. I=
t utilizes deep learning models, such as Large Language Models (LLMs), to r=
ecognize and replicate data patterns, enabling the generation of human-like=
 content. Notable families of LLMs include GPT (GPT-3.5, GPT-3.5 Turbo, and=
 GPT-4), LLaMA (LLaMA and LLaMA-2), and Mistral (Mistral and Mixtral). GPT,=
 which stands for Generative Pretrained Transformer, is especially popular =
for text generation and is widely used in applications like ChatGPT. GenAI =
has taken the world by storm and revolutionized various industries, includi=
ng healthcare, finance, and entertainment. However, GenAI models have sever=
al limitations, including biases from training data, generating factually i=
ncorrect information, and difficulty in understanding complex content. Addi=
tionally, their performance can vary based on domain specificity.<br><br><b=
r>In recent times, Knowledge Graphs (KGs) have attracted considerable atten=
tion for their ability to represent structured and interconnected informati=
on, and adopted by many companies in various domains. KGs represent knowled=
ge by depicting relationships between entities, known as facts, usually bas=
ed on formal ontological models. Consequently, they enable accuracy, decisi=
veness, interpretability, domain-specific knowledge, and evolving knowledge=
 in various AI applications. The intersection between GenAI and KG has igni=
ted significant interest and innovation in Natural Language Processing (NLP=
). For instance, by integrating LLMs with KGs during pre-training and infer=
ence, external knowledge can be incorporated for enhancing the model=E2=80=
=99s capabilities and improving interpretability. When integrated, they off=
er a robust approach to problem solving in diverse areas such as informatio=
n enrichment, representation learning, conversational AI, cross-domain AI t=
ransfer, bias, content generation, and semantic understanding. This worksho=
p aims at reinforcing the relationships between Deep Learning, Knowledge Gr=
aphs, and NLP communities and foster interdisciplinary research in the area=
 of GenAI.<br>-------------------------------------------------------------=
--------------------<br>Topics of Interest<br>-----------------------------=
----------------------------------------------------<br>* Enhancing KG cons=
truction and completion with GenAI<br>=C2=A0 =C2=A0* Multimodal KG generati=
on<br>=C2=A0 =C2=A0* Text-to-KG using LLMs<br>=C2=A0 =C2=A0* Multilingual K=
Gs<br>* GenAI for KG embeddings<br>* GenAI for Temporal KGs<br>* Dialogue s=
ystems enhanced by KG and GenAI<br>* Cross-domain knowledge transfer with G=
enAI<br>* Bias mitigation using KGs in GenAI<br>* Explainability with KGs a=
nd GenAI<br>* Natural language querying of KGs via GenAI<br>* NLP tasks usi=
ng KGs and GenAI<br>* Prompt Engineering using KGs<br>* GenAI for Ontology =
learning and schema induction in KGs<br>* Hybrid QA systems combining KGs a=
nd GenAI<br>* Recommendation systems and KGs with GenAI<br>* Creating bench=
mark datasets relevant for tasks combining KGs and GenAI<br>* Real-world ap=
plications on scholarly data, biomedical domain, etc.<br>* Knowledge Graph =
Alignment<br>* Applying to real-world scenarios<br>------------------------=
------------------------------------------------------------<br>Important D=
ates<br>-------------------------------------------------------------------=
-----------------<br>- Submission deadline: 5 November 2024<br>- Notificati=
on of Acceptance: 5 December 2024<br>- Camera-ready paper due: 13 December =
2024<br>- COLING2025 Workshop day: 19 January 2025<br>---------------------=
---------------------------------------------------------------<br>Submissi=
ons<br>--------------------------------------------------------------------=
----------------<br>Full research papers (6-8 pages)<br>Short research pape=
rs (4-6 pages)<br>Position papers (2 pages)<br><br><br>These page limits on=
ly apply to the main body of the paper. At the end of the paper (after the =
conclusions but before the references) papers need to include a mandatory s=
ection discussing the limitations of the work and, optionally, a section di=
scussing ethical considerations. Papers can include unlimited pages of refe=
rences and an unlimited appendix.<br><br><br>Papers must follow the two-col=
umn format of *ACL conferences, using the official templates (<a href=3D"ht=
tps://www.overleaf.com/latex/templates/association-for-computational-lingui=
stics-acl-conference/jvxskxpnznfj/" target=3D"_blank">https://www.overleaf.=
com/latex/templates/association-for-computational-linguistics-acl-conferenc=
e/jvxskxpnznfj/</a>). The templates are available for download as style fil=
es and formatting guidelines. Submissions that do not adhere to the specifi=
ed styles, including paper size, font size restrictions, and margin width, =
will be desk-rejected. Submissions are open to all and must be anonymous, a=
dhering to COLING 2025&#39;s double-blind submission and reproducibility gu=
idelines.=C2=A0 All accepted papers =C2=A0(after double-blind review of at =
least 3 experts) will appear in the workshop proceedings that will be publi=
shed in ACL Anthology.<br><br><br>At least one of the authors of the accept=
ed papers must register for the workshop to be included into the workshop p=
roceedings. The workshop will be a 100% in-person 1-day event at COLING 202=
5.<br><br><br>Submissions must be made using the START portal: <a href=3D"h=
ttps://softconf.com/coling2025/GenAIK25/" target=3D"_blank">https://softcon=
f.com/coling2025/GenAIK25/</a> <br><br><br>--------------------------------=
-------------------------------------------------<br>Sponsors<br>----------=
-----------------------------------------------------------------------<br>=
NFDI4DataScience (NFDI4DS - <a href=3D"https://www.nfdi4datascience.de/" ta=
rget=3D"_blank">https://www.nfdi4datascience.de/</a>) is a national researc=
h data infrastructure for Data Science and AI project. The overarching obje=
ctive of the project is the development, establishment, and sustainment of =
a national research data infrastructure (NFDI) for the Data Science and Art=
ificial Intelligence community in Germany. The vision of NFDI4DS is to supp=
ort all steps of the complex and interdisciplinary research data lifecycle,=
 including collecting/creating, processing, analyzing, publishing, archivin=
g, and reusing resources in Data Science and Artificial Intelligence. NFDI4=
ds is offering a total of =E2=82=AC2000 in travel grants (=E2=82=AC1000 eac=
h) to two selected students who will attend and present their work at GenAI=
K 2025! To be considered, submit your paper to the workshop, and if your pa=
per is accepted, you=E2=80=99ll be eligible for a chance to receive one of =
the two grants.<br><br>----------------------------------------------------=
-----------------------------<br>Organization<br>--------------------------=
-------------------------------------------------------<br>- <a href=3D"htt=
ps://www.fiz-karlsruhe.de/en/forschung/lebenslauf-und-publikationen-dr-ing-=
genet-asefa-gesese">Genet Asefa Gesese</a>, FIZ Karlsruhe, KIT, Germany<br>=
- <a href=3D"https://www.fiz-karlsruhe.de/de/bereiche/lebenslauf-prof-dr-ha=
rald-sack">Harald Sack</a>, FIZ Karlsruhe, KIT, Germany<br>- <a href=3D"htt=
ps://www.uni-mannheim.de/dws/people/professors/prof-dr-heiko-paulheim/">Hei=
ko Paulheim</a>, University of Mannheim, Germany<br>- <a href=3D"https://ww=
w.albertmeronyo.org/">Albert Mero=C3=B1o-Pe=C3=B1uela</a>, King=E2=80=99s C=
ollege London, UK<br>- <a href=3D"https://chenlihu.com/">Lihu Chen</a>, Imp=
erial College London, UK<br><br>If you have published in ACL conferences pr=
eviously, and are interested to be part of the program committee of GenAIK2=
025, please fill in this form.<br clear=3D"all"><div><br></div><span class=
=3D"gmail_signature_prefix">-- </span><br><div dir=3D"ltr" class=3D"gmail_s=
ignature" data-smartmail=3D"gmail_signature"><div dir=3D"ltr"><div><font co=
lor=3D"#993366" face=3D"Tahoma, serif, EmojiFont"><b>Dr.-Ing.=C2=A0</b></fo=
nt><font size=3D"1" style=3D"color:rgb(0,0,0);font-family:Tahoma,serif,Emoj=
iFont;font-size:16px"><span style=3D"font-size:13px"><font color=3D"#993366=
"><b>Genet Asefa Gesese</b></font></span></font></div><div><font size=3D"1"=
 style=3D"color:rgb(0,0,0);font-family:Tahoma,serif,EmojiFont;font-size:16p=
x"><span style=3D"font-size:13px">Head of Machine Learning Department (</sp=
an></font><font color=3D"#000000" face=3D"Tahoma, serif, EmojiFont">Abteilu=
ngsleitung Maschinelles Lernen</font><span style=3D"color:rgb(0,0,0);font-f=
amily:Tahoma,serif,EmojiFont;font-size:13px">)</span></div><div style=3D"co=
lor:rgb(0,0,0);font-family:Calibri,Helvetica,sans-serif,EmojiFont,&quot;App=
le Color Emoji&quot;,&quot;Segoe UI Emoji&quot;,NotoColorEmoji,&quot;Segoe =
UI Symbol&quot;,&quot;Android Emoji&quot;,EmojiSymbols;font-size:16px"><spa=
n style=3D"font-family:Tahoma,serif,EmojiFont;font-size:13px">FIZ Karlsruhe=
 =E2=80=93 Leibniz Institute for Information Infrastructure</span><br></div=
><div><font face=3D"Tahoma, serif, EmojiFont"><font color=3D"#000000">( </f=
ont><font color=3D"#0000ee"><u><a href=3D"https://www.fiz-karlsruhe.de/en/b=
ereiche/lebenslauf-und-publikationen-dr-ing-genet-asefa-gesese" target=3D"_=
blank">https://www.fiz-karlsruhe.de/en/bereiche/lebenslauf-und-publikatione=
n-dr-ing-genet-asefa-gesese</a></u></font><font color=3D"#000000">=C2=A0)</=
font></font><br></div><div style=3D"color:rgb(0,0,0);font-family:Calibri,He=
lvetica,sans-serif,EmojiFont,&quot;Apple Color Emoji&quot;,&quot;Segoe UI E=
moji&quot;,NotoColorEmoji,&quot;Segoe UI Symbol&quot;,&quot;Android Emoji&q=
uot;,EmojiSymbols;font-size:16px"><font size=3D"1" style=3D"font-family:Tah=
oma,serif,EmojiFont"><span style=3D"font-size:13px"><font color=3D"#993366"=
>AND</font></span></font></div><div><font><font color=3D"#993366"><font fac=
e=3D"Tahoma, serif, EmojiFont">Karlsruhe Institute of Technology (KIT)=C2=
=A0 =C2=A0 =C2=A0 =C2=A0=C2=A0</font></font></font></div><div><font><font c=
olor=3D"#993366"><font face=3D"Tahoma, serif, EmojiFont"><u>(=C2=A0<a href=
=3D"https://www.aifb.kit.edu/web/Genet_Asefa_Gesese/en" target=3D"_blank">h=
ttps://www.aifb.kit.edu/web/Genet_Asefa_Gesese/en</a>=C2=A0)</u></font><br>=
</font></font></div></div></div></div>
</div>

--00000000000078dd2b06254f51d2--

--===============4771275518343244041==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
Institute mailing list
[email protected]
Unsubscribe via https://lists.uvic.ca/mailman/listinfo/institute

--===============4771275518343244041==--