Back to the future: A logical framework for temporal information representation and inferencing from financial news

Temporal information carries information about changes and time of the changes. Consider a company investing in another company. The former may choose to inject the money gradually with the amount and frequency depending on the performance of the latter. This shows that an event can be completed in multiple steps and at any given time before completion, it is partially completed. Thus, the status of an event at any time could be described by some degree of completion. One can make inference based on such temporal information to predict what event(s) would likely happen next. The prediction could be made not only based on the completed or partially completed events in the past, but also based on the correlation between the events, which have taken place (i.e. executed events), and the ones planned (i.e. planned events). This process of making inference based on the executed and planned temporal events is described lively as "Back to the Future" and can be considered as part of the formally-called temporal information inference. Existing temporal information processing frameworks (e.g., temporal database, temporal information extraction, and temporal logic), however, are ineffective for this purpose. This paper defines a novel logical framework for two-dimensional (i.e., executed and planned time lines) temporal information representing and inferencing. An operational model realising the logical framework in financial news data is also addressed.