Abstract

Chinese event extraction uses word embedding to capture similarity, but suffers when handling previously unseen or rare words. From the test, we know that characters may provide some information that we cannot obtain in words, so we propose a novel architecture for combining word representations: character–word embedding based on attention and semantic features. By using an attention mechanism, our method is able to dynamically decide how much information to use from word or character level embedding. With the semantic feature, we can obtain some more information about a word from the sentence. We evaluate different methods on the CEC Corpus, and this method is found to improve performance. View Full-Text