Traditionally, machine learning approaches for information extraction require human annotated data that can be costly and time-consuming to produce. However, in many cases, there ...
Abstract. Data-to-text generation systems tend to be knowledge-based and manually built, which limits their reusability and makes them time and cost-intensive to create and maintai...
We have developed two systems, FN and ANDD, that use natural language and graphical displays, respectively, to communicate information about objects to human users. Both systems m...
: This article examines information theory from the aspect of its "conduit metaphor." A historical approach and a close reading of certain texts by Warren Weaver and Nor...
Recent years have seen increasing attention in temporal processing of texts as well as a lot of standardization effort of temporal information in natural language. A central part ...