Document-Level Event Role Filler Extraction Using Key-Value Memory Network

Previous work has demonstrated that end-to-end neural sequence models well for document-level event role filler extraction. However, the network model suffers from problem of not being able to utilize global information, resulting in incomplete extraction arguments. This is because inputs BiLSTM are all single-word vectors with no input contextual information. phenomenon particularly pronounced at document level. To address this problem, we propose key-value memory networks enhance and overall represented two levels: sentence-level document-level. At sentence-level, use obtain key sentence document-level, a representations by recording information about those words articles sensitive similarity. We fuse levels means fusion formula. perform various experimental validations on MUC-4 dataset, results show using works better than other models.