Document-level information is very important for event detection even at sentence level. In this paper, we propose a novel Document Embedding Enhanced Bi-RNN model, called DEEB-RNN, to detect events in sentences. This model first learns event detection oriented embeddings of documents through a hierarchical and supervised attention based RNN, which pays word-level attention to event triggers and sentence-level attention to those sentences containing events. It then uses the learned document embedding to enhance another bidirectional RNN model to identify event triggers and their types in sentences. Through experiments on the ACE-2005 dataset, we demonstrate the effectiveness and merits of the proposed DEEB-RNN model via comparison with state-of-the-art methods.
Information selection is the most important component in document summarization task. In this paper, we propose to extend the basic neural encoding-decoding framework with an information selection layer to explicitly model and optimize the information selection process in abstractive document summarization. Specifically, our information selection layer consists of two parts: gated global information filtering and local sentence selection. Unnecessary information in the original document is first globally filtered, then salient sentences are selected locally while generating each summary sentence sequentially. To optimize the information selection process directly, distantly-supervised training guided by the golden summary is also imported. Experimental results demonstrate that the explicit modeling and optimizing of the information selection process improves document summarization performance significantly, which enables our model to generate more informative and concise summaries, and thus significantly outperform state-of-the-art neural abstractive methods. * This work was done while the first author was doing internship at Baidu Inc.
Event extraction is useful for many practical applications, such as news summarization and information retrieval. However, the popular automatic context extraction (ACE) event extraction program only defines very limited and coarse event schemas, which may not be suitable for practical applications. FrameNet is a linguistic corpus that defines complete semantic frames and frame-to-frame relations. As frames in FrameNet share highly similar structures with event schemas in ACE and many frames actually express events, we propose to redefine the event schemas based on FrameNet. Specifically, we extract frames expressing event information from FrameNet and leverage the frame-to-frame relations to build a hierarchy of event schemas that are more fine-grained and have much wider coverage than ACE. Based on the new event schemas, we propose a joint event extraction approach that leverages the hierarchical structure of event schemas and frame-to-frame relations in FrameNet. The extensive experiments have verified the advantages of our hierarchical event schemas and the effectiveness of our event extraction model. We further apply the results of our event extraction model on news summarization. The results show that the summarization approach based on our event extraction model achieves significant better performance than several state-ofthe-art summarization approaches, which also demonstrates that the hierarchical event schemas and event extraction model are promising to be used in the practical applications.
Stochastic game theoretic framework has been used in many fields of networks with interactive behaviors. However, further use of this framework is limited due to the following reasons. Firstly, it is difficult to build comprehensive and rigorous models for complex network structures by the state-based game model. Secondly, solving and extending the dynamic behaviors of participators of the network are nearly impossible, because of the complexity of state transitions. Last but not least, general game model is not able to describe and analyze specific events and behaviors in some kinds of networks, like enterprise networks. In this paper, we propose a new modeling paradigm (stochastic game net, or SGN) for stochastic games representation with Petri nets. Based on our graphical tool, stochastic game problems can be described clearly, and the model can be solved and extended easily. Moreover, this paper puts forth a series of methods for modeling and analyzing the competitive game by SGN, which is the main contribution of this work. Our achievements are applied to the security analysis for enterprise networks. The analysis results prove the powerful ability of our achievements in solving the complicated and dynamic game problems. Furthermore, our approaches can be used to calculate the existence and the value of an equilibrium point.
Recent neural sequence-to-sequence models have shown significant progress on short text summarization. However, for document summarization, they fail to capture the longterm structure of both documents and multisentence summaries, resulting in information loss and repetitions. In this paper, we propose to leverage the structural information of both documents and multi-sentence summaries to improve the document summarization performance. Specifically, we import both structural-compression and structuralcoverage regularization into the summarization process in order to capture the information compression and information coverage properties, which are the two most important structural properties of document summarization. Experimental results demonstrate that the structural regularization improves the document summarization performance significantly, which enables our model to generate more informative and concise summaries, and thus significantly outperforms state-of-the-art neural abstractive methods.
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.