English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Commonsense Properties from Query Logs and Question Answering Forums

MPS-Authors
/persons/resource/persons212613

Razniewski,  Simon
Databases and Information Systems, MPI for Informatics, Max Planck Society;

/persons/resource/persons239661

Pal,  Koninika
Databases and Information Systems, MPI for Informatics, Max Planck Society;

/persons/resource/persons239663

Sakhadeo,  Archit
Databases and Information Systems, MPI for Informatics, Max Planck Society;

/persons/resource/persons45720

Weikum,  Gerhard
Databases and Information Systems, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)

arXiv:1905.10989.pdf
(Preprint), 767KB

Supplementary Material (public)
There is no public supplementary material available
Citation

Romero, J., Razniewski, S., Pal, K., Pan, J. Z., Sakhadeo, A., & Weikum, G. (2019). Commonsense Properties from Query Logs and Question Answering Forums. Retrieved from http://arxiv.org/abs/1905.10989.


Cite as: http://hdl.handle.net/21.11116/0000-0003-FEEE-4
Abstract
Commonsense knowledge about object properties, human behavior and general concepts is crucial for robust AI applications. However, automatic acquisition of this knowledge is challenging because of sparseness and bias in online sources. This paper presents Quasimodo, a methodology and tool suite for distilling commonsense properties from non-standard web sources. We devise novel ways of tapping into search-engine query logs and QA forums, and combining the resulting candidate assertions with statistical cues from encyclopedias, books and image tags in a corroboration step. Unlike prior work on commonsense knowledge bases, Quasimodo focuses on salient properties that are typically associated with certain objects or concepts. Extensive evaluations, including extrinsic use-case studies, show that Quasimodo provides better coverage than state-of-the-art baselines with comparable quality.