Towards Task-Based Temporal Extraction and Recognition

We seek to improve the robustness and portability of tem- poral information extraction systems by incorporating data-driven tech- niques. We present two sets of experiments pointing us in this direction. The first shows that machine-learning-based recognition of temporal ex- pressions not only achieves high accuracy on its own but can also improve rule-based normalization. The second makes use of a staged normaliza- tion architecture to experiment with machine learned classifiers for cer- tain disambiguation sub-tasks within the normalization task.