Dependency parsing is a task of extracting the relationships between words in a sentence. Researchers have achieved great success in transition-based and graph-based methods recently. However, there are problems of error propagation and high time complexity. This paper proposes dependency parser based on reinforcement learning to improve transition-based parser. We regard the actions in transition-based method as RL agent's actions. Meanwhile, we introduce a BACK action, so that the agent can get back to the previous state after entering the error state. We use the Universal Dependencies dataset to make experiments on different language. Experiments show that this method effectively solves the problem of error propagation of transition-based method and improve the accuracy significantly.
In this paper, we present a practical method of sentence ordering in extractive multi-document summarization tasks of Chinese language. By using Support Vector Machine (SVM), we classify the sentences of a summary into several groups in rough position according to the source documents. Then we adjust the sentence sequence of each group according to the estimation of directional relativity of adjacent sentences, and find the sequence of each group. Finally, we connect the sequences of different groups to generate the final order of the summary. Experimental results indicate that this method works better than most existing methods of sentence ordering.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.