SenseHive

A research project funded by Croatian Science Foundation that tries to make sense of word meanings through the effort of a crowd of native language speakers. The capacity to understand different word meanings would make the computers better at many important tasks − search, translation, question answering, and even user interaction.

Description

SenseHive is a research project that tackles the problem of the iterative and semi-automatic construction of a lexico-semantic resources using crowdsourcing. Our goal is to create a crowdsourcing platform for collecting word usage data from everyday language speakers. Empowered by the latest insights from natural language processing and machine learning, SenseHive gradually builds a network representing the word meanings through the efforts of a large crowd of people who are eager to help.

We think that making computers better at understanding different word meanings would benefit many important tasks — search, translation, question answering, and even user interaction.

To find out more about this project, check out the project website.

Project fact sheet

Funder: Croatian Science Foundation (CSF)
Funding: 820.000,00 HRK
Funding scheme: Installation Research Projects UIP-09-2014 / Uspostavni istraživački projekti UIP-09-2014
Grant number: Grant UIP-2014-09-7312
Principal investigator (PI): Assoc. Prof. Jan Šnajder
Participants: TakeLab and partners: Faculty of Humanities and Social Sciences, University of Zagreb; Faculty of Arts, University of Ljubljana; Institute for Natural Language Processing, University of Stuttgart.
Duration: 3 years (2015 – 2018)