Bingquan Liu

Drug-Named Entity Recognition (DNER) for biomedical literature is a fundamental facilitator of Information Extraction. For this reason, the DDIExtraction2011 (DDI2011) and DDIExtraction2013 (DDI2013) challenge introduced one task aiming at recognition of drug names. State-of-the-art DNER approaches heavily rely on hand-engineered features and domain-specific knowledge which are difficult to collect and define. Therefore, we offer an automatic exploring words and characters level features approach: a recurrent neural network using bidirectional long short-term memory (LSTM) with Conditional Random Fields decoding (LSTM-CRF). Two kinds of word representations are used in this work: word embedding, which is trained from a large amount of text, and character-based representation, which can capture orthographic feature of words. Experimental results on the DDI2011 and DDI2013 dataset show the effect of the proposed LSTM-CRF method. Our method outperforms the best system in the DDI2013 challenge.

随着在线社会网络为其用户提供的功能不断丰富,用户可以参加多种多样的社交活动,将这些活动表示为对应种类的事件.其中一些事件包括多个用户之间的交互行为,再由这些交互的类型来决定该事件的最终结果.将每个行为表示为用户之间的链接,用链接的极性值来表示交互的类型,对于这些链接值预测的研究称为链接预测.研究者们对于链接预测问题提出了很多方法,其中大多是在静态网络环境中孤立地预测每条链接边的值.他们将这类事件中的用户行为看作"普通的用户行为",即这些链接被看成独立且离散的存在,并未考虑这些链接之间在事件生成中的内在联系.本文通过将事件中用户行为表示为"序列行为",提出了基于序列行为的链接值预测和事件结果预测的方法.该方法能将这种序列信息建模,在模型中这种序列信息得以累积,利用这种累积来预测序列中下一个或多个时刻的链接值.在完成对整个序列的预测的同时,通过累积信息可以推断出该事件的结果.实验结果表明,我们的方法明显优于静态、孤立的链接预测方法,而且可以更好地推断出包含该序列行为事件的最终结果. With the development of on-line social networks, increasing numbers of functions are provided to social members. These social members can join different kinds of activities that are presented as events. Some events may include many user-interaction behaviors, and the results of such events are determined by the kinds of behaviors. If each behavior is presented as a link, the sign value of the link may represent the kind of behavior. Link prediction is the focus for predicting the value of these links. Many studies have been performed on solving link-prediction problems. However, most of them were performed in static network environments, and each link was predicted independent of the others. Those researchers treated user behavior for such events as "normal behavior," which were treated individually and discretely. Therefore, the correlation of those links that were created during the event was not considered. In this paper, we model these event behaviors as "sequence behavior", and proposed sequence-behavior-based link-prediction and event-prediction methods. In our method, we can accumulate the sequence information of behaviors, and can predict the next one or several link values in the sequence. When we finish predicting the entire sequence, the event's result may be inferred. The experiment results show that our method outperforms the static and individual link-prediction methods. The event's result may be better predicted at the same time.

In some online social network services (SNSs), the members are allowed to label their relationships with others, and such relationships can be represented as the links with signed values (positive or negative). The networks containing such relations are named signed social networks (SSNs), and some real-world complex systems can be also modeled with SSNs. Given the information of the observed structure of an SSN, the link prediction aims to estimate the values of the unobserved links. Noticing that most of the previous approaches for link prediction are based on the members’ similarity and the supervised learning method, however, research work on the investigation of the hidden principles that drive the behaviors of social members are rarely conducted. In this paper, the deep belief network (DBN)-based approaches for link prediction are proposed. Including an unsupervised link prediction model, a feature representation method and a DBN-based link prediction method are introduced. The experiments are done on the datasets from three SNSs (social networking services) in different domains, and the results show that our methods can predict the values of the links with high performance and have a good generalization ability across these datasets.

Identification of protein binding sites is critical for studying the function of the proteins. In this paper, we proposed a method for protein binding site prediction, which combined the order profile propensities and hidden Markov support vector machine (HM-SVM). This method employed the sequential labeling technique to the field of protein binding site prediction. The input features of HM-SVM include the profile-based propensities, the Position-Specific Score Matrix (PSSM), and Accessible Surface Area (ASA). When tested on different data sets, the proposed method showed promising results, and outperformed some closely relative methods by more than 10% in terms of AUC.