Financial fraud, such as money laundering, is known to be a serious process of crime that makes illegitimately obtained funds go to terrorism or other criminal activity. This kind of illegal activities involve complex networks of trade and financial transactions, which makes it difficult to detect the fraud entities and discover the features of fraud. Fortunately, trading/transaction network and features of entities in the network can be constructed from the complex networks of the trade and financial transactions. The trading/transaction network reveals the interaction between entities, and thus anomaly detection on trading networks can reveal the entities involved in the fraud activity; while features of entities are the description of entities, and anomaly detection on features can reflect details of the fraud activities. Thus, network and features provide complementary information for fraud detection, which has potential to improve fraud detection performance. However, the majority of existing methods focus on networks or features information separately, which does not utilize both information. In this paper, we propose a novel fraud detection framework, CoDetect, which can leverage both network information and feature information for financial fraud detection. In addition, the CoDetect can simultaneously detecting financial fraud activities and the feature patterns associated with the fraud activities. Extensive experiments on both synthetic data and real-world data demonstrate the efficiency and the effectiveness of the proposed framework in combating financial fraud, especially for money laundering.

The rapid growth of scientific papers makes it difficult to find relevant and appropriate citations. Contextaware citation recommendation aims to overcome this problem by providing a list of scientific papers given a short passage of text. In this paper, we propose a LSTM based model for context-aware citation recommendation, which firstly learns the distributed representations of the citation contexts and the scientific papers separately based on LSTM, and then measures the relevance based on the learned distributed representation of citation contexts and the scientific papers. Finally, the scientific papers with high relevance scores are selected as the recommendation list. In particular, we try to incorporate author information, venue information and content information in scientific paper distributed vector representation. Furthermore, we integrate author information of the given context in citation context distributed vector representation. Thus the proposed model makes personalized context-aware citation recommendation possible, which is a new issue that few papers addressed in the past. When conducting experiments on the ACL Anthology Network (AAN) and DBLP datasets, the results demonstrate the proposed LSTM based model for context-aware citation recommendation is able to achieve considerable improvement over previous context-aware citation recommendation approaches. The personalized recommendation approach is also competitive with the non-personalized recommendation approach.

Automatically generating the impression section of a radiology report given the findings section can summarize as much salient information of the findings section as possible, thus promoting more effective communication between radiologists and referring physicians. To significantly reduce the workload of radiologists, we develop and evaluate a novel framework of abstractive summarization methods to automatically generate the impression section of chest radiology reports. Despite recent advancements in the natural language process (NLP) field such as BERT and its variants, existing abstractive summarization models and methods could not be directly applied to radiology reports, partly due to domain-specific radiology terminology. In response, we develop a pre-trained language model in the chest radiology domain, named ChestXRayBERT, to solve the problem of automatically summarizing chest radiology reports. Specifically, we first collect radiology-related scientific papers as pre-training corpus and pre-train a ChestXRayBERT on it. Then, an abstractive summarization model is proposed, which consists of the pre-trained ChestXRayBERT and a Transformer decoder. Finally, the model is fine-tuned on chest X-ray reports for the abstractive summarization task. When evaluated on the publicly available OPEN-I and MIMIC-CXR datasets, the performance of our proposed model achieves significant improvement compared with other neural network based abstractive summarization models. In general, the proposed ChestXRayBERT demonstrates the feasibility and promise of tailoring and extending advanced NLP techniques to the domain of medical imaging and radiology, as well as in the broader biomedicine and healthcare fields in the future.

Fast-growing scientific papers pose the problem of rapidly and accurately finding a list of reference papers for a given manuscript. Citation recommendation is an indispensable technique to overcome this obstacle. In this paper, we propose a citation recommendation approach via mutual reinforcement on a three-layered graph, in which each paper, author or venue is represented as a vertex in the paper layer, author layer, and venue layer, respectively. For personalized recommendation, we initiate the random walk separately for each query researcher. However, this has a high computational complexity due to the large graph size. To solve this problem, we apply a three-layered interactive clustering approach to cluster related vertices in the graph. Personalized citation recommendations are then made on the subgraph, generated by the clusters associated with each researcher's needs. When evaluated on the ACL anthology network, DBLP, and CiteSeer ML data sets, the performance of our proposed model-based citation recommendation approach is comparable with that of other state-of-the-art citation recommendation approaches. The results also demonstrate that the personalized recommendation approach is more effective than the nonpersonalized recommendation approach.

With the increasing number of scientific papers, researchers find it more and more difficult to obtain relevant and appropriate papers to cite. Citation recommendation aims to overcome this problem by providing a reference paper list for a given manuscript. In this paper, we propose a bibliographic network representation (BNR) model, which simultaneously incorporates bibliographic network structure and content of different kinds of objects (authors, papers and venues) for efficient recommendation. The proposed model also makes personalized citation recommendation possible, which is a new issue that a few papers addressed in the past. When conducting experiments on the ACL Anthology Network (AAN) and DBLP datasets, the results demonstrate the proposed BNR based citation recommendation approach is able to achieve considerable improvement over other network representation based citation recommendation approaches. The performance of the personalized recommendation approach is also competitive with the non-personalized recommendation approach.