@article{Zeng_Feng_Ma_Wang_Yan_Shi_Zhao_2018, title={Scale Up Event Extraction Learning via Automatic Training Data Generation}, volume={32}, url={https://ojs.aaai.org/index.php/AAAI/article/view/12030}, DOI={10.1609/aaai.v32i1.12030}, abstractNote={ <p> The task of event extraction has long been investigated in a supervised learning paradigm, which is bound by the number and the quality of the training instances. Existing training data must be manually generated through a combination of expert domain knowledge and extensive human involvement. However, due to drastic efforts required in annotating text, the resultant datasets are usually small, which severally affects the quality of the learned model, making it hard to generalize. Our work develops an automatic approach for generating training data for event extraction. Our approach allows us to scale up event extraction training instances from thousands to hundreds of thousands, and it does this at a much lower cost than a manual approach. We achieve this by employing distant supervision to automatically create event annotations from unlabelled text using existing structured knowledge bases or tables.We then develop a neural network model with post inference to transfer the knowledge extracted from structured knowledge bases to automatically annotate typed events with corresponding arguments in text.We evaluate our approach by using the knowledge extracted from Freebase to label texts from Wikipedia articles. Experimental results show that our approach can generate a large number of highquality training instances. We show that this large volume of training data not only leads to a better event extractor, but also allows us to detect multiple typed events. </p> }, number={1}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Zeng, Ying and Feng, Yansong and Ma, Rong and Wang, Zheng and Yan, Rui and Shi, Chongde and Zhao, Dongyan}, year={2018}, month={Apr.} }