Companion Proceedings of the Web Conference 2022
No TL;DR found
Abstract
Question Answering (QA) is increasingly used by search engines to provide\nresults to their end-users, yet very few websites currently use QA technologies\nfor their search functionality. To illustrate the potential of QA technologies\nfor the website search practitioner, we demonstrate web searches that combine\nQA over knowledge graphs and QA over free text -- each being usually tackled\nseparately. We also discuss the different benefits and drawbacks of both\napproaches for web site searches. We use the case studies made of websites\nhosted by the Wikimedia Foundation (namely Wikipedia and Wikidata). Differently\nfrom a search engine (e.g. Google, Bing, etc), the data are indexed integrally,\ni.e. we do not index only a subset, and they are indexed exclusively, i.e. we\nindex only data available on the corresponding website.\n