Can One Language Bootstrap the Other: A Case Study on Event Extraction

This paper proposes a new bootstrapping framework using cross-lingual information projection. We demonstrate that this framework is particularly effective for a challenging NLP task which is situated at the end of a pipeline and thus suffers from the errors propagated from upstream processing and has low-performance baseline. Using Chinese event extraction as a case study and bitexts as a new source of information, we present three bootstrapping techniques. We first conclude that the standard mono-lingual bootstrapping approach is not so effective. Then we exploit a second approach that potentially benefits from the extra information captured by an English event extraction system and projected into Chinese. Such a crosslingual scheme produces significant performance gain. Finally we show that the combination of mono-lingual and cross-lingual information in bootstrapping can further enhance the performance. Ultimately this new framework obtained 10.1% relative improvement in trigger labeling (F-measure) and 9.5% relative improvement in argument labeling.