Equip** machines with comprehensive knowledge of the world's entities and their
relationships has been a longstanding goal of AI. Over the last decade, large-scale …

Existing techniques for unionable table search define unionability using metadata (tables
must have the same or similar schemas) or column-based metrics (for example, the values …

Conversational question answering (ConvQA) tackles sequential information needs where
contexts in follow-up questions are left implicit. Current ConvQA systems operate over …

In conversational question answering, users express their information needs through a
series of utterances with incomplete context. Typical ConvQA methods rely on a single …

Quantitative data is important in many domains. Information extraction methods draw
structured data from documents. However, the extraction of quantities and their contexts has …

Clinical trials are essential for drug development but often suffer from expensive, inaccurate
and insufficient patient recruitment. The core problem of patient-trial matching is to find …

Temporal question answering (QA) involves time constraints, with phrases such as"... in
2019" or"... before COVID". In the former, time is an explicit condition, in the latter it is implicit …

Large amounts of geospatial data have been made available recently on the linked open
data cloud and on the portals of many national cartographic agencies (eg, OpenStreetMap …

Providing machines with comprehensive knowledge of the world's entities and their
relationships has been a long-standing vision and challenge for AI. Over the last 15 years …

Machine knowledge about the world's entities should include quantity properties, such as
heights of buildings, running times of athletes, energy efficiency of car models, energy …