With the rapid growth of online medical platforms, more and more doctors are willing to manage and communicate with patients via online services. Considering the large volume and various patient conditions, identifying and classifying patients' medical records has become a crucial problem. To efficiently index these records, a common practice is to annotate them with semantically meaningful tags. However, manual labeling tags by doctors is impractical due to the possibility of thousands of tag candidates, which necessitates a tag recommender system. Due to the long tail distribution of tags and the dominance of low-activity doctors, as well as the unique uploaded medical records, this task is rather challenging. This paper proposes an efficient doctor specific tag recommendation framework for improved medical record management without side information. Specifically, we first utilize effective language models to learn the text representation. Then, we construct a doctor embedding learning module to enhance the recommendation quality by integrating implicit information within text representations and considering latent tag correlations to make more accurate predictions. Extensive experiment results demonstrate the effectiveness of our framework from the viewpoints of all doctors (20% improvement) or low-activity doctors (10% improvement).

Gene Ontology (GO) is the primary gene function knowledge base that enables computational tasks in biomedicine. The basic element of GO is a term, which includes a set of genes with the same function. Existing research efforts of GO mainly focus on predicting gene term associations. Other tasks, such as generating descriptions of new terms, are rarely pursued. In this paper, we propose a novel task: GO term description generation. This task aims to automatically generate a sentence that describes the function of a GO term belonging to one of the three categories, i.e., molecular function, biological process, and cellular component. To address this task, we propose a Graph-in-Graph network that can efficiently leverage the structural information of GO. The proposed network introduces a two-layer graph: the first layer is a graph of GO terms where each node is also a graph (gene graph). Such a Graph-in-Graph network can derive the biological functions of GO terms and generate proper descriptions. To validate the effectiveness of the proposed network, we build three large-scale benchmark datasets. By incorporating the proposed Graph-in-Graph network, the performances of seven different sequence-to-sequence models can be substantially boosted across all evaluation metrics, with up to 34.7%, 14.5%, and 39.1% relative improvements in BLEU, ROUGE-L, and METEOR, respectively.

Vision-and-language (V-L) tasks require the system to understand both vision content and natural language, thus learning fine-grained joint representations of vision and language (a.k.a. V-L representations) is of paramount importance. Recently, various pre-trained V-L models are proposed to learn V-L representations and achieve improved results in many tasks. However, the mainstream models process both vision and language inputs with the same set of attention matrices. As a result, the generated V-L representations are entangled in one common latent space . To tackle this problem, we propose DiMBERT (short for Di sentangled M ultimodal-Attention BERT ), which is a novel framework that applies separated attention spaces for vision and language, and the representations of multi-modalities can thus be disentangled explicitly. To enhance the correlation between vision and language in disentangled spaces, we introduce the visual concepts to DiMBERT which represent visual information in textual format. In this manner, visual concepts help to bridge the gap between the two modalities. We pre-train DiMBERT on a large amount of image–sentence pairs on two tasks: bidirectional language modeling and sequence-to-sequence language modeling. After pre-train, DiMBERT is further fine-tuned for the downstream tasks. Experiments show that DiMBERT sets new state-of-the-art performance on three tasks (over four datasets), including both generation tasks (image captioning and visual storytelling) and classification tasks (referring expressions). The proposed DiM (short for Di sentangled M ultimodal-Attention) module can be easily incorporated into existing pre-trained V-L models to boost their performance, up to a 5% increase on the representative task. Finally, we conduct a systematic analysis and demonstrate the effectiveness of our DiM and the introduced visual concepts.

Diagnosis prediction aims to forecast diseases that a patient might have in his next hospital visit, which is critical in Clinical Decision Supporting System (CDSS). Existing approaches mainly formulate diagnosis prediction as a multi-label classification problem and use discrete medical codes as major features. While the structural information among medical codes and time series data in clinical data are generally neglected. In this paper, we propose Multi-modal Clinical Data based Hierarchical Multi-label model (MHM) to integrate discrete medical codes, structural information and time series data into the same framework for diagnosis prediction task. Experimental results on two real world datasets demonstrate the superiority of proposed MHM over state-of-the-art approaches.

Given a set of objects P and a set of ranking functions F over P, an interesting problem is to compute the top ranked objects for all functions. Evaluation of multiple top-k queries finds application in systems, where there is a heavy workload of ranking queries (e.g., online search engines and product recommendation systems). The simple solution of evaluating the top-k queries one-by-one does not scale well; instead, the system can make use of the fact that similar queries share common results to accelerate search. This paper is the first, to our knowledge, thorough study of this problem. We propose methods that compute all top-k queries in batch. Our first solution applies the block indexed nested loops paradigm, while our second technique is a view-based algorithm. We propose appropriate optimization techniques for the two approaches and demonstrate experimentally that the second approach is consistently the best. Our approach facilitates evaluation of other complex queries that depend on the computation of multiple top-k queries, such as reverse top-k and top-m influential queries. We show that our batch processing technique for these complex queries outperform the state-of-the-art by orders of magnitude.

Given a collection of objects that carry both spatial and textual information, a spatio-textual similarity join retrieves the pairs of objects that are spatially close and textually similar. As an example, consider a social network with spatially and textually tagged persons (i.e., their locations and profiles). A useful task (for friendship recommendation) would be to find pairs of persons that are spatially close and their profiles have a large overlap (i.e., they have common interests). Another application is data de-duplication (e.g., finding photographs which are spatially close to each other and high overlap in their descriptive tags). Despite the importance of this operation, there is very little previous work that studies its efficient evaluation and in fact under a different definition; only the best match for each object is identified. In this paper, we combine ideas from state-of-the-art spatial distance join and set similarity join methods and propose efficient algorithms that take into account both spatial and textual constraints. Besides, we propose a batch processing technique which boosts the performance of our approaches. An experimental evaluation using real and synthetic datasets shows that our optimized techniques are orders of magnitude faster than base-line solutions.