Count Knowledge
Extracting Entity Counts
Cont information is the relation between an entity and a set of entities that can be expressed individually, as X is an employee of Z, Y is an employee of Z or as a cardinality Z has N employees. Identifying such information in text and knowledge bases (KBs) and linking the two variants can
- identify incomplete entity enumerations
- ground counts in representative entities
- identify KB inconsistencies
- enhance downstream tasks like search and question answering
Most research focus on numerical facts without joining the dots between numerical facts specifying cardinal information and their corresponding entity-to-entity grounding facts. Popular general-purpose KBs have limited ability to recognize such predicates.
Class Cardinality
We first tackle the problem of class cardinality comparison by identifying three related problems of varying informativeness and approachability.
- Cardinality estimation
- Proportionality etimation
- Dominance estimation
We show how using an aggregate of different cardinality signals of different types and from different sources, we are able to better identify the bigger of two classes.
Publications
9. Shrestha Ghosh, Simon Razniewski, Damien Graux, Gerhard Weikum. CardiO: Predicting Cardinality from Online Sources. (Web Conference 2024) [pdf] [poster] [code|data]
8. Simon Razniewski, Hiba Arnaout, Shrestha Ghosh, Fabian M Suchanek. Completeness, Recall, and Negation in Open-World Knowledge Bases: A Survey. (ACM Computing Surveys 2024) [pdf]
7. Shrestha Ghosh. Limits of Zero-shot Probing on Object Prediction. (Knowledge Base Construction from Pre-trained Language Models workshop at International Semantic Web Conference (ISWC) 2023) [pdf] [code]
6. Shrestha Ghosh, Simon Razniewski, Gerhard Weikum. Class Cardinality Comparison as a Fermi Problem. (Web Conference 2023) [pdf] [poster] [code|data]
5. Shrestha Ghosh, Simon Razniewski, Gerhard Weikum. CoQEx: Entity Counts Explained. (WSDM 2023) [pdf] [poster] [video]
4. Shrestha Ghosh, Simon Razniewski, Gerhard Weikum. Answering Count Questions with Structured Answers from Text. (JoWS 2022) [arxiv|journal]
3. Shrestha Ghosh, Simon Razniewski, Gerhard Weikum. Answering Count Queries with Explanations. (SIGIR 2022) [pdf] [poster] [code|data]
2. Shrestha Ghosh, Simon Razniewski, Gerhard Weikum. Uncovering Hidden Semantics of Set Information in Knowledge Bases. Journal of Web Semantics (JWS 2020) [pdf] [code|data]
1. Shrestha Ghosh, Simon Razniewski, Gerhard Weikum. CounQER: A System for Discovering and Linking Count Information in Knowledge Bases. (ESWC 2020) [pdf] [demo] [poster]