Temponym Tagging: Temporal Scopes for Textual Phrases

Erdal Kuzey, Jannik Strötgen, Vinay Setty, Gerhard Weikum

Abstract: For many NLP and IR applications, anchored temporal information extracted from textual documents is of utmost importance. Thus, temporal tagging -- the extraction and normalization of temporal expressions -- has gained a lot of attention in recent years and several tools such as HeidelTime and SUTime are proposed. However, such tools do not address textual phrases with temporal scopes like "Clinton's time as First Lady". While such phrases (so-called temponyms) are not temporal expressions per se, information about their temporal scopes can be helpful in many scenarios, e.g., in the context of temporal information retrieval. In this paper, we describe the integration of a wide range of temponyms to the publicly available temporal tagger HeidelTime to include temponym tagging.