Modeling Document-level Temporal Structures for Building Temporal Dependency Graphs
This addresses the challenge of temporal relation extraction in natural language processing, particularly for news documents, with an incremental improvement over existing methods.
The paper tackles the problem of building temporal dependency graphs by modeling document-level temporal structures using news discourse profiling, showing that this approach effectively identifies distant inter-sentence event/time expression pairs that are temporally related and otherwise difficult to locate.
We propose to leverage news discourse profiling to model document-level temporal structures for building temporal dependency graphs. Our key observation is that the functional roles of sentences used for profiling news discourse signify different time frames relevant to a news story and can, therefore, help to recover the global temporal structure of a document. Our analyses and experiments with the widely used knowledge distillation technique show that discourse profiling effectively identifies distant inter-sentence event and (or) time expression pairs that are temporally related and otherwise difficult to locate.