Things such as organizations, persons, or locations are all around us, particularly in the news, forum posts, facebook updates, and tweets. With named things, we can introduce background in news articles, summarize articles, build question-answering systems, and much more. However, it is challenging to find and link them, as they often may be ambiguous. In this work, we aim to enrich the knowledge graph Wikidata with new relations and things only found in the articles of multilingual Wikipedia. The long term goal is the development of a multilingual system that can answer any natural question and improve how we find new relevant information.
Speaker: Dr Marcus Klang, Department of Computer Science, Lund University
The Corona crisis prevents physical meetings and discussions, but in order to continue dialogue and joint learning, we now offer a series of online lunch seminars. Together we watch one or more presentations from previous AI Lund events for 20-30 minutes. Then an expert, often the original speaker, are there to answer questions for 10-15 minutes. You can also ask questions in the text chat during the video. The presentations can be in Swedish or English, and you can ask questions in both languages. On May 13 we watch the presentation that Dr Marcus Klang gave at the AI Lund fika-to-fika workshop on AI Technologies 30 August 2019. Title: Finding Things in Strings