Neural attention-based encoders, which effectively attend sentence tokens to their associated context without being restricted by long-term distance or dependency, have demonstrated outstanding performance in embedding sentences into meaningful representations (embeddings). The Universal Sentence Encoder (USE) is one of the most well-recognized deep neural network (DNN) based solutions, which is facilitated with an attention-driven transformer architecture and has been pre-trained on a large number of sentences from the Internet. Besides the fact that USE has been widely used in many downstream applications, including information retrieval (IR), interpreting its complicated internal working mechanism remains challenging. In this work, we present a visual analytics solution towards addressing this challenge. Specifically, focused on semantics and syntactics (concepts and relations) that are critical to domain clinical IR, we designed and developed a visual analytics system, i.e., USEVis. The system investigates the power of USE in effectively extracting sentences’ semantics and syntactics through exploring and interpreting how linguistic properties are captured by attentions. Furthermore, by thoroughly examining and comparing the inherent patterns of these attentions, we are able to exploit attentions to retrieve sentences/documents that have similar semantics or are closely related to a given clinical problem in IR. By collaborating with domain experts, we demonstrate use cases with inspiring findings to validate the contribution of our work and the effectiveness of our system.

Neural embeddings are widely used in language modeling and feature generation with superior computational power. Particularly, neural document embedding - converting texts of variable-length to semantic vector representations - has shown to benefit widespread downstream applications, e.g., information retrieval (IR). However, the black-box nature makes it difficult to understand how the semantics are encoded and employed. We propose visual exploration of neural document embedding to gain insights into the underlying embedding space, and promote the utilization in prevalent IR applications. In this study, we take an IR application-driven view, which is further motivated by biomedical IR in healthcare decision-making, and collaborate with domain experts to design and develop a visual analytics system. This system visualizes neural document embeddings as a configurable document map and enables guidance and reasoning; facilitates to explore the neural embedding space and identify salient neural dimensions (semantic features) per task and domain interest; and supports advisable feature selection (semantic analysis) along with instant visual feedback to promote IR performance. We demonstrate the usefulness and effectiveness of this system and present inspiring findings in use cases. This work will help designers/developers of downstream applications gain insights and confidence in neural document embedding, and exploit that to achieve more favorable performance in application domains.

Road is a great part of transportation, emergency response and disaster relief, the monitor and real-time evaluation of the state of road are always important for the rescue works after disaster. SAR has some advantages of all-weather and all-time, which can be well adapted to disaster conditions. Until now the extraction of road damage information has been studied more in optical remote sensing, while less in SAR images. Base on the researches in optical and the studies of road information extraction in SAR, we explored the road damage information extraction in this paper, and proposed a new method of road damage information extraction.

This paper developed a method of mapping wet snow and dry snow in alpine terrain based on multi-polarimetric and mono temporal ASAR data in the snow melting season.14 ASAR images were used to obtain the variation of the backscattering coefficients of snow covered areas in the snow melting process. Shi's method combining intensity and polarization property is taken as a reference to retrieve wet snow. DEM data was also used to retrieve dry snow. In order to verify the accuracy of the result, we made a scale conversion to images resulting from the ASAR data to match with the MODIS image and found an overall accuracy of 82.04%. The Google Earth image was also used as an aided verification. The results are all found to show a good estimation of the snow covered areas.

Discovering contrasts between collections of data is an important task in data mining. In this paper, we introduce a new type of contrast pattern, called a minimal distinguishing subsequence (MDS). An MDS is a minimal subsequence that occurs frequently in one class of sequences and infrequently in sequences of another class. It is a natural way of representing strong and succinct contrast information between two sequential datasets and can be useful in applications such as protein comparison, document comparison and building sequential classification models. Mining MDS patterns is a challenging task and is significantly different from mining contrasts between relational/transactional data. One particularly important type of constraint that can be integrated into the mining process is the maximum gap constraint. We present an efficient algorithm called ConSGapMiner, to mine all MDSs according to a maximum gap constraint. It employs highly efficient bitset and Boolean operations, for powerful gap based pruning within a prefix growth framework. A performance evaluation with both sparse and dense datasets, demonstrates the scalability of ConSGapMiner and shows its ability to mine patterns from high dimensional datasets at low supports.