Time

We present a novel semantic framework for modeling temporal relations and event durations that maps pairs of events to real valued scales for the purpose of constructing document-level event timelines.

Using our framework, we construct the largest temporal relation dataset to date, and use it to train a variety of neural models to jointly predict finegrained (real-valued) temporal relations and event durations, showing not only that our models obtain strong results on our dataset, the representations they learn can be straightforwardly transferred to the standard categorical relation datasets with competitive performance.

Data

References

Researchers

Siddharth Vashishtha

Aaron Steven White

Benjamin Van Durme