Hiba Arnaout

I'm a PhD candidate at the Max Planck Institute for Informatics, a member of the Databases and Information Systems Group (advisors: Prof. Gerhard Weikum and Dr. Simon Razniewski). During my PhD I interned at The University of Edinburgh (mentor: Jeff Z. Pan) and at Bosch Center for Artificial Intelligence (mentor: Daria Stepanova). Previously, I received my Master's of Computer Science from The American University of Beirut (advisor: Shady Elbassuoni).

My research interests include knowledge bases, information retrieval, text mining.



Publications


(newest to oldest)

UnCommonSense in Action! Informative Negations for Commonsense Knowledge Bases.
Hiba Arnaout, Tuan-Phong Nguyen, Simon Razniewski, and Gerhard Weikum
WSDM 2023

We present a web portal to explore informative negations about everyday concepts: (i) in a research-focused interface, users get a glimpse into the methodology behind the system; (ii) in a trivia interface, users can explore negative statements about concepts of their choice; and (iii) in a query interface, users can query the knowledge base using explicit negative relations.

[DEMO] - [PAPER]

demo paper




UnCommonSense: Informative Negative Knowledge about Everyday Concepts.
Hiba Arnaout, Simon Razniewski, Gerhard Weikum, and Jeff Z. Pan
CIKM 2022 Acceptance rate 23%

We introduce UnCommonSense, a method for discovering expressive negative statements about everyday concepts such as elephant, pancake, and newspaper. The method significantly outperforms the state-of-the-art. Given a target concept, UnCommonSense exploits existing information about type siblings to infer interesting seed negative statements. It then scrutinizes and ranks the potentially large set by informativeness. We release a large dataset with more than 6 million informative negations as a resource for future research.

[WEBPAGE] - [PAPER] - [SLIDES] - [POSTER]

conference paper




Utilizing Language Model Probes for Knowledge Graph Repair.
Hiba Arnaout, Trung-Kien Tran, Daria Stepanova, Mohamed Hassan Gad-Elrab, Simon Razniewski, and Gerhard Weikum
Wikiworkshop at WWW 2022

We present a method to repair incorrect statements in existing knowledge bases by replacing incorrect triples with likely correct ones, thus avoiding information loss. Our method explores the power of LM probes to achieve this goal and shows that context retrieval from the knowledge base itself can significantly boost the probing. We conduct experiments on two web-scale knowledge bases where we outperform a prior baseline..

[PAPER]

workshop paper




Negative Statements Considered Useful.
Hiba Arnaout, Simon Razniewski, Gerhard Weikum, and Jeff Z. Pan
JWS 2021
[WEBPAGE] - [PAPER]

journal paper


Negative Knowledge for Open-world Wikidata.
Hiba Arnaout, Simon Razniewski, Gerhard Weikum, and Jeff Z. Pan
WWW Companion 2021
[PAPER]

workshop paper


Neguess: Wikidata-entity Guessing Game with Negative Clues.
Aditya B. Biswas, Hiba Arnaout, and Simon Razniewski
ISWC 2021
[DEMO] - [PAPER]

demo paper


Wikinegata: A Knowledge Base with Interesting Negative Statements.
Hiba Arnaout, Simon Razniewski, Gerhard Weikum, and Jeff Z. Pan
VLDB 2021
[DEMO] - [PAPER]

demo paper


Enriching Knowledge Bases with Interesting Negative Statements.
Hiba Arnaout, Simon Razniewski, and Gerhard Weikum
AKBC 2020 Audience-choice best paper award (voted by conference attendees)
[WEBPAGE] - [PAPER] - [SLIDES]

conference paper


Biological Knowledge Graph Construction, Search, and Navigation.
Chandana Tennakoon, Nazar Zaki, Hiba Arnaout, Shady Elbassuoni, Wassim El-Hajj, and Alanoud Al Jaberi
Academic Press 2019
[BOOK] - [CHAPTER]

book chapter


Effective Searching of RDF Knowledge Graphs.
Hiba Arnaout and Shady Elbassuoni
JWS 2018 Presented at ISWC 2018
[PAPER] - [SLIDES]

journal paper


Top-k Keyword Search over Wikipedia-based RDF Knowledge Graphs.
Hrag Yoghourdjian, Shady Elbassuoni, Mohamad Jaber, and Hiba Arnaout
KDIR 2017 Best student paper award nominee
[PAPER]

conference paper


Result Diversity for RDF Search.
Hiba Arnaout and Shady Elbassuoni
KDIR 2016
[PAPER]

conference paper




Talks


  • Negative Statements Considered Useful, invited talk at the Institute for Language, Cognition and Computation (ILCC), The University of Edinburgh, 2022. [SLIDES]
  • Completeness, Recall, and Negation in Open-World Knowledge Bases (with Simon Razniewski, Shrestha Ghosh, and Fabian Suchanek), tutorial at KR 2021, ISWC 2021, and WWW 2022. [WEBPAGE]
  • On the Limits of Machine Knowledge (with Simon Razniewski, Shrestha Ghosh, and Fabian Suchanek), tutorial at VLDB 2021. [WEBPAGE]
  • Enriching Knowledge Bases with Interesting Negative Statements, Forum for presentations of significant Semantic Web-related research at ISWC 2020.




Experience


  • Researcher
    Max Planck Institute for Informatics
    Feb 2018 - exp. May 2023
    Saarbrücken, Germany
  • Research Intern
    Bosch Center for Artificial Intelligence
    Jun 2021 - Mar 2022
    Renningen, Germany
  • Visiting Researcher
    The University of Edinburgh
    Feb 2020 - Aug 2020
    Edinburgh, United Kingdom
  • Document Control Administrator
    American University of Beirut
    Jan 2016 – Dec 2017
    Beirut, Lebanon
  • Research Assistant
    American University of Beirut
    Feb 2014 – Jan 2018
    Beirut, Lebanon
  • IT Instructor
    American University of Beirut & United Nations
    Mar 2017 – Sep 2017
    Beirut, Lebanon
  • Teaching Assistant
    American University of Beirut
    Feb 2014 – Dec 2016
    Beirut, Lebanon




Miscellaneous


Service
  • Reviewer: JWS ('22), EMNLP ('21,'22), IJCAI ('21,'22), CIKM ('20,'21), ISWC ('20, '21), ACL ('20).
  • Volunteer: VLDB ('21).

Scholarships and Awards
  • Reward for invention Knowledge Graph Repair Using Ontologies and LMs, Bosch, 2022.
  • Participated in discussion, DFG grant of 312,000 € for compiling negative knowledge at web scale, 2021.
  • Audience-choice Best Paper Award at AKBC, 2020.
  • Best Student Paper Award Nominee at IC3K'17, 2017.
  • Full Graduate Assistantship at the American University of Beirut, 2014.

Student Supervision
  • Aditya Bikram Biswas (Master's student), 2021.
  • Mang Zhao (Master's student), 2018.

Other Activities
  • Attended Reasoning Web Summer School, RW, 2019.
  • Attended Lisbon Machine Learning School, LxMLS, 2018.






Contact


    harnaout[at]mpi-inf.mpg.de - Twitter