Paper: Granularity in Natural Language Discourse

ACL ID W11-0143
Title Granularity in Natural Language Discourse
Venue IWCS
Session Main Conference
Year 2011

This paper discusses the phenomenon of granularity in natural language1. By ‘granularity’ we mean the level of detail of description of an event or object. Humans can seamlessly shift their gran- ularity perspective while reading or understanding a text. To emulate this mechanism, we describe a set of features that identify the levels of granularity in text, and empirically verify this feature set using a human annotation study for granularity identification. This theory is the foundation for any system that can learn the (global) behavior of event descriptions from (local) behavior descriptions. This is the first research initiative, to our knowledge, for identifying granularity shifts in natural language descriptions.