Automated content moderation for collaborative knowledge hubs like Wikipedia or Wikidata is an important yet challenging task due to multiple factors. In this paper, we construct a database of discussions happening around articles marked for deletion in several Wikis and in three languages, which we then use to evaluate a range of LMs on different tasks (from predicting the outcome of the discussion to identifying the implicit policy an individual comment might be pointing to). Our results reveal, among others, that discussions leading to deletion are easier to predict, and that, surprisingly, self-produced tags (keep, delete or redirect) don't always help guiding the classifiers, presumably because of users' hesitation or deliberation within comments.

I'll be talking about ChatGPT, artificial intelligence, and why I don't think we're doomed. I'll start by admitting that I'm a human. I've been using software and search engines while researching and writing this post. So what you are reading has been tarnished by technology's terrible taint. Looking at it another way, today's tech has helped me find facts and arrange my ideas. I also strongly suspect that using today's technology has affected how I write. If I'd lived in an earlier era -- mayhap composing with goose quills, iron gall ink and cotton paper -- I might be writing stuff like "The Dunwich Horror". And yes, mayhap is a real word; although it's not used much these days.1 "…As before, the sides of the road shewed a bruising indicative of the blasphemously stupendous bulk of the horror; whilst the conformation of the tracks seemed to argue a passage in two directions…." Even in Lovecraft's day, there was only one Lovecraft.2 I'll also admit to a bias.

Recent work has utilised knowledge-aware approaches to natural language understanding, question answering, recommendation systems, and other tasks. These approaches rely on well-constructed and large-scale knowledge graphs that can be useful for many downstream applications and empower knowledge-aware models with commonsense reasoning. Such knowledge graphs are constructed through knowledge acquisition tasks such as relation extraction and knowledge graph completion. This work seeks to utilise and build on the growing body of work that uses findings from the field of natural language processing (NLP) to extract knowledge from text and build knowledge graphs. The focus of this research project is on how we can use transformer-based approaches to extract and contextualise event information, matching it to existing ontologies, to build a comprehensive knowledge of graph-based event representations. Specifically, sub-event extraction is used as a way of creating sub-event-aware event representations. These event representations are then further enriched through fine-grained location extraction and contextualised through the alignment of historically relevant quotes.

Quotes of public figures can mark turning points in history. A quote can explain its originator's actions, foreshadowing political or personal decisions and revealing character traits. Impactful quotes cross language barriers and influence the general population's reaction to specific stances, always facing the risk of being misattributed or taken out of context. The provision of a cross-lingual knowledge graph of quotes that establishes the authenticity of quotes and their contexts is of great importance to allow the exploration of the lives of important people as well as topics from the perspective of what was actually said. In this paper, we present QuoteKG, the first multilingual knowledge graph of quotes. We propose the QuoteKG creation pipeline that extracts quotes from Wikiquote, a free and collaboratively created collection of quotes in many languages, and aligns different mentions of the same quote. QuoteKG includes nearly one million quotes in $55$ languages, said by more than $69,000$ people of public interest across a wide range of topics. QuoteKG is publicly available and can be accessed via a SPARQL endpoint.