Templet: A Collaborative System for Knowledge Graph Question Answering over Wikidata.

We present Templet: an online question answering (QA) system for Wikidata. Templet is based on the collaboratively-edited repository QAWiki, which collects questions in multiple natural languages along with their corresponding structured queries. Templet generates templates from question–query pairs on QAWiki by replacing key entities with identifiers. Using autocompletion, the user can type a question in natural language, select a template, and again using autocompletion, select the entities they wish to insert into the template’s placeholders, generating a concrete question, query and results. The main objectives of Templet are: (i) to enable users to answer potentially complex questions over Wikidata using natural language templates and autocompletion; (ii) to encourage users to collaboratively create new templates via QAWiki, which in turn can benefit not only Templet, but other QA systems.