A Survey on Temporal Reasoning for Temporal Information Extraction from Text (Extended Abstract)

Time is deeply woven into how people perceive, and communicate about the\nworld. Almost unconsciously, we provide our language utterances with temporal\ncues, like verb tenses, and we can hardly produce sentences without such cues.\nExtracting temporal cues from text, and constructing a global temporal view\nabout the order of described events is a major challenge of automatic natural\nlanguage understanding. Temporal reasoning, the process of combining different\ntemporal cues into a coherent temporal view, plays a central role in temporal\ninformation extraction. This article presents a comprehensive survey of the\nresearch from the past decades on temporal reasoning for automatic temporal\ninformation extraction from text, providing a case study on the integration of\nsymbolic reasoning with machine learning-based information extraction systems.\n