Saeedeh Shekarpour

Assistant Professor
Department of Computer Science
University of Dayton
James Lee

News and Opportunities

  • I am founding CANAB: Cognitive ANalytics lAB in the University of Dayton, looking for talented, hardworking and passionate students.

Research Areas

I am passionate to conduct advanced research in the folowing fields

  1. Knowledge representation in AI technologies
    • learning quality embeddings for ontological concepts, relations
    • transforming semi-structured data like XML to embeddings
    • extracting knowledge from text and publishing based on the principles of Linked Open Data
  2. Cognitive computing in Question Answering (QA) and chatbot technologies
    • Query Expansion, Query Rewriting, Query Disambiguation
    • Perception models for chatbot technology
    • Integration platforms for component-wise QA systems
  3. Web science
    • social content analytics
    • Semantic social network
  4. NLP, deep learning and ontology-based approaches in the biomedical domain
    • Learning embeddings for biomedical literature
    • Organizing relations or entity consolidation
    • Fact extraction in the biomedical domain

Selected Publications

You can find the full list of my publications in Google Scholar, DBLP and Research Gate entries. In the following there are a selected ones on the word class conferences or journals.

  • Why Reinvent the Wheel-Let's Build Question Answering Systems Together. Kuldeep Singh, Sethupat, A, Andreas Both, Saeedeh Shekarpour, Lytra, I, Usbeck, R, Vyas, A, Khikmatullaev, A, Punjani, D, Christoph Lange, Vidal, M-E, Jens Lehmann, Sören Auer. The Web Conference (WWW 2018)
  • Nitish Aggarwal, Saeedeh Shekarpour, Sumit Bhatia and Amit Sheth. Tutorial of Knowledge Graph in Theory and Practice, CIKM 2017 [ SLIDES].
  • Saeedeh Shekarpour, Edgards Marx, Sören Auer, and Amit Sheth. RQUERY: Rewriting Natural Language Queries on Knowledge Graphs to Alleviate the Vocabulary Mismatch Problem. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence AAAI-17
  • Andreas Both, Dennis Diefenbach, Kuldeep Singh, Saeedeh Shekarpour, Didier Cherix, Christoph Lange: Qanary - A Methodology for Vocabulary-Driven Open Question Answering Systems. ESWC2016
  • Saeedeh Shekarpour, Edgard Marx, Axel-Cyrille Ngonga Ngomo, Sören Auer: SINA: Semantic interpretation of user queries for question answering on interlinked data. J. Web Sem. 2015
  • Saeedeh Shekarpour, Axel-Cyrille Ngomo, Sören Auer: Question answering on interlinked data. WWW 2013
  • Saeedeh Shekarpour, S. D. Katebi: Modeling and evaluation of trust with an extension in semantic web. J. Web Sem. 2010
  • Saeedeh Shekarpour, Sören Auer, Axel-Cyrille Ngonga Ngomo, Daniel Gerber, Sebastian Hellmann, Claus Stadler: Keyword-Driven SPARQL Query Generation Leveraging Background Knowledge. Web Intelligence 2011

Resources: Ontology, Vocabulary, Lexicon, Corpus

We are committed to publishing open-source resources that can be used by the community of researchers for education, evaluation, testing, and comparison.
  • CEVO: Comprehensive EVent Ontology Enhancing Cognitive Annotation (CEVO) [1] built on Levin’s conceptual hierarchy of English verbs that categorizes verbs with the shared meaning and syntactic behavior. The motivation of this work comes from the fact that there is a deficiency in research on the abstract conceptualization required to organize relations. Abstract conceptualization can benefit various communities and applications such as NLP, information extraction, and ML.
  • empathi: an ontology for Emergency Managing and Planning about Hazard Crises [2]. In the domain of emergency management during hazard crises, having sufficient situational awareness information is critical. It conceptualizes the core concepts concerning with the domain of emergency managing and planning of hazard crises.
  • A quality type-aware annotated corpus and lexicon for harassment research: provided both a quality annotated corpus and an offensive words lexicon capturing different types of harassment content: (i) sexual, (ii) racial, (iii) appearance-related, (iv) intellectual, and (v) political. This corpus consists of 25,000 annotated tweets for the five types of harassment content [3].
  • qa ontology is a message-driven vocabulary built upon an abstract level. This vocabulary is concluded from the conceptual views of different QA systems. It enables researchers and industry to implement message-driven QA systems and to reuse and extend different approaches without interoperability and extension concerns [4].
  1. Saeedeh Shekarpour, Faisal alshargi, Valerie L. Shalin, Krishnaprasad Thirunarayan, Amit P. Sheth: CEVO: Comprehensive EVent Ontology Enhancing Cognitive Annotation. ICSC 2019
  2. Manas Gaur, Saeedeh Shekarpour, Amelie Gyrard, Amit P. Sheth: empathi: An ontology for Emergency Managing and Planning about Hazard Crisis. ICSC 2019
  3. Mohammadreza Rezvan, Saeedeh Shekarpour, Lakshika Balasuriya, Krishnaprasad Thirunarayan, Valerie L. Shalin, Amit P. Sheth: A Quality Type-aware Annotated Corpus and Lexicon for Harassment Research. WebSci 2018: 33-36 Best of WebSci (Top-5)
  4. Kuldeep Singh, Andreas Both, Dennis Diefenbach, Saeedeh Shekarpour: Towards a Message-Driven Vocabulary for Promoting the Interoperability of Question Answering Systems. ICSC 2016: 386-389

Presentations and Talks (Selected)

  • Web Scie 2018, Harassment corpus and lexicon, Amsterdam, Netherland, May 2018.
  • “Using Knowledge Graph for Promoting Cognitive Computing”, IBM research 2017 , Almaden, California.
  • QA Tutorial in Web Intelligence Summer School, Saint-Etienne, France, Sep 2015.
  • “SINA: a semantic search engine” in IBM Research Center (Watson project-DeepQA) , NY, USA, Dec 2013.
  • World Wide Web Conference(WWW 2013) , Rio de Janeiro, Brazil, May 2013.
  • Joint International Semantic Technology Conference(JIST2012), Nara, Japan. Dec 2012.
  • International Semantic Web Conference(ISWC 2011), Bonn, Germany, Oct 2011.
  • Web Intelligence Conference(WIIA 2011), Lyon, France, Aug 2011.

Current Projects

  • 2019: Developing a cognitive Engine for Chatbot Technology
  • 2018-present: Learning Domain-specific Embeddings for Knowledge Graphs and Text
  • 2018-present: Knowledge Extraction and Management

Past Projects

  • Knowledge Graph 2016-present
  • Harassment 2017: Context-Aware Harassment Detection on Social Media.
  • HazardsSEES 2016-2017: Social and Physical Sensing Enabled Decision Support.
  • WDAQUA 2015: Answering Questions using Web Data.
  • SINA 2010-2014: Semantic Interpretation of Natural Language questions towards question Answering.