Temporal Information Extraction by Predicting Relative Time-lines
This addresses a bottleneck in temporal information extraction for NLP applications, offering a novel approach to timeline construction.
The paper tackles the problem of constructing linear timelines from temporal relations in text, proposing a new paradigm that directly predicts event start and end points, bypassing intermediate relation prediction, and reports promising results.
The current leading paradigm for temporal information extraction from text consists of three phases: (1) recognition of events and temporal expressions, (2) recognition of temporal relations among them, and (3) time-line construction from the temporal relations. In contrast to the first two phases, the last phase, time-line construction, received little attention and is the focus of this work. In this paper, we propose a new method to construct a linear time-line from a set of (extracted) temporal relations. But more importantly, we propose a novel paradigm in which we directly predict start and end-points for events from the text, constituting a time-line without going through the intermediate step of prediction of temporal relations as in earlier work. Within this paradigm, we propose two models that predict in linear complexity, and a new training loss using TimeML-style annotations, yielding promising results.