This paper proposes a dependency-driven scheme to dynamically determine the syntactic parse tree structure for tree kernel- based anaphoricity determination in coreference resolution. Given a full syntactic parse tree...
详细信息
This paper proposes a dependency-driven scheme to dynamically determine the syntactic parse tree structure for tree kernel- based anaphoricity determination in coreference resolution. Given a full syntactic parse tree, it keeps the nodes and the paths related with current mention based on constituent dependencies from both syntactic and semantic perspectives, while removing the noisy information, eventually leading to a dependency-driven dynamic syntactic parse tree (D-DSPT). Evaluation on the ACE 2003 corpus shows that the D-DSPT outperforms all previous parse tree structures on anaphoricity determination, and that applying our anaphoricity determination module in coreference resolution achieves the so far best performance.
Recent kernel-based PPI extraction systems achieve promising performance because of their capability to capture structural syntactic information, but at the expense of computational complexity. This paper incorporates...
详细信息
Recent kernel-based PPI extraction systems achieve promising performance because of their capability to capture structural syntactic information, but at the expense of computational complexity. This paper incorporates dependency information as well as other lexical and syntactic knowledge in a feature-based framework. Our motivation is that, considering the large amount of biomedical literature being archived daily, feature-based methods with comparable performance are more suitable for practical applications. Additionally, we explore the difference of lexical characteristics between biomedical and newswire domains. Experimental evaluation on the AIMed corpus shows that our system achieves comparable performance of 54.7 in F1-Score with other state-of-the-art PPI extraction systems, yet the best performance among all the feature-based ones.
This paper proposes a unified framework for zero anaphora resolution, which can be divided into three sub-tasks: zero anaphor detection, anaphoricity determination and antecedent identification. In particular, all the...
详细信息
This paper presents a topic-driven framework for generating a generic summary from multi-documents. Our approach is based on the intuition that, from the statistical point of view, the summary's probability distri...
详细信息
Electronic patient record mining deals with the implicit and useful medical information stored in the electronic patient record *** this technology the useful knowledge is extracted and the scientific and auxiliary de...
详细信息
With the development of the 3G technology, M-learning enters a period of rapid development. But meanwhile 3G also restrains the development of M-Iearning due to several drawbacks in its early days. According to the ap...
详细信息
This paper proposes a new scheme to determine the tree span structure for tree kernel-based anaphoricity determination in coreference resolution. Given a sentence and current mention, it gets all the dependencies, enc...
详细信息
Side chain packing is a crucial step for protein structure prediction. And the quality of rotamer library has important implications in side chain packing. This paper assess dunbrack rotamer libraries and simple sampl...
详细信息
We present an identity-based encryption in the relative-leakage model. In our construction, we firstly make use of a notion of new cryptographic primitive, identity-based hash proof system(IB-HPS), to construct a leak...
详细信息
ISBN:
(纸本)9788988678251
We present an identity-based encryption in the relative-leakage model. In our construction, we firstly make use of a notion of new cryptographic primitive, identity-based hash proof system(IB-HPS), to construct a leakage-resilient IB-HPS based on a simple assumption and also prove its security by the variant of dual system encryption. Then, based on our IB-HPS scheme, we construct directly an efficient leakage-resilient identity-based encryption(IBE) scheme in the model.
In this paper, we first propose a specification approach combining interface automata and Z language. This approach can be used to describe temporal properties and data properties of software components. A branching t...
详细信息
ISBN:
(纸本)9788988678213
In this paper, we first propose a specification approach combining interface automata and Z language. This approach can be used to describe temporal properties and data properties of software components. A branching time logic for ZIAs is presented. We then give an algorithm for model checking this logic on ZIAs with finite domain. Furthermore, we present a mu-calculus logic for ZIAs, and give a model checking algorithm for this logic.
暂无评论