An Analysis of Bootstrapping for the Recognition of Temporal Expressions

We present a semi-supervised (bootstrapping) approach to the extraction of time expression mentions in large unlabelled corpora. Because the only supervision is in the form of seed examples, it becomes necessary to resort to heuristics to rank and filter out spurious patterns and candidate time expressions. The application of bootstrapping to time expression recognition is, to the best of our knowledge, novel. In this paper, we describe one such architecture for bootstrapping Information Extraction (IE) patterns —suited to the extraction of entities, as opposed to events or relations— and summarize our experimental findings. These point out to the fact that a pattern set with a good increase in recall with respect to the seeds is achievable within our framework while, on the other side, the decrease in precision in successive iterations is succesfully controlled through the use of ranking and selection heuristics. Experiments are still underway to achieve the best use of these heuristics and other parameters of the bootstrapping algorithm.