For the task of time-series data classification (TSC), some methods directly classify raw time-series (TS) data. However, certain sequence features are not evident in the time domain and the human brain can extract visual features based on visualization to classify data. Therefore, some researchers have converted TS data to image data and used image processing methods for TSC. While human perceptionconsists of a combination of human senses from different aspects, existing methods only use sequence features or visualization features. Therefore, this paper proposes a framework for TSC based on fusion features (TSC-FF) of sequence features extracted from raw TS and visualization features extracted from Area Graphs converted from TS. Deep learning methods have been proven to be useful tools for automatically learning features from data; therefore, we use long short-term memory with an attention mechanism (LSTM-A) to learn sequence features and a convolutional neural network with an attention mechanism (CNN-A) for visualization features, in order to imitate the human brain. In addition, we use the simplest visualization method of Area Graph for visualization features extraction, avoiding loss of information and additional computational cost. This article aims to prove that using deep neural networks to learn features from different aspects and fusing them can replace complex, artificially constructed features, as well as remove the bias due to manually designed features, in order to avoid the limitations of domain knowledge. Experiments on several open data sets show that the framework achieves promising results, compared with other methods.

Nowadays, data is being generated, collected, and analyzed at an unprecedented scale, data integration is the problem of combining data from heterogeneous, autonomous data sources, and providing users with a unified view of integrated data. To design a data integration framework, we need to address challenges, such as schema mapping, data cleaning, record linkage, and data fusion. In this paper, we briefly introduce the traditional data integration approaches, and then, a novel graph-based data integration framework based on unified concept model (UCM) is proposed to address real-world refueling data integration problems. Within this framework, schema mapping was carried out and metadata from heterogeneous sources is integrated in a UCM. UCM has the benefits of being easy to update. It is also important for effective schema mapping and data transformation. By following the structure of UCM, data from different sources is automatically transformed into instance data and linked together by using semantic similarity computation metrics, finally the data is stored in graph database. Experiments are carried out based on heterogeneous data from refueling records, social networks of astroturfers, and vehicle trajectories. Experimental results and reference implementation demonstrations show good precision and recall of the proposed framework.

Multilingual pre-trained language models (mPLMs) have achieved remarkable performance on zero-shot cross-lingual transfer learning. However, most mPLMs implicitly encourage cross-lingual alignment in pre-training stage, making it hard to capture accurate word alignment across languages. In this paper, we propose Word-align ADapters for Cross-lingual transfer (WAD-X) to explicitly align word representations of mPLMs via language-specific subspace. Taking a mPLM as the backbone model, WAD-X constructs subspace for each source-target language pair via adapters. The adapters use statistical alignment as the prior knowledge to guide word-level aligning in the corresponding bilingual semantic subspace. We evaluate our model across a set of target languages on three zero-shot cross-lingual transfer tasks: part-of-speech tagging (POS), dependency parsing (DP), and sentiment analysis (SA). Experimental results demonstrate that our proposed model improves zero-shot cross-lingual transfer on three benchmarks, with improvements of 2.19, 2.50, and 1.61 points in POS, DP, and SA tasks over strong baselines.

Distant supervised relation extraction (DSRE) is widely used to extract novel relational facts from plain text, so as to improve the knowledge graph. However, distant supervision inevitably suffers from the noisy labeling problem that will severely damage the performance of relation extraction. Currently, most DSRE methods are mainly focused on reducing the weights of noisy sentences, ignoring the bag-level noise where all sentences in a bag are wrongly labeled. In this paper, we present a novel noise detection-based relation extraction approach (NDRE) to automatically detect noisy labels with entity information and dynamically correct them, which can alleviate both instance-level and bag-level noisy problems. By this means, we can extend the dataset from the Web tables without introducing more noise. In this approach, to embed the semantics of sentences from corpus and web tables, we firstly propose a powerful sentence coder that employs an internal multi-head self-attention mechanism between the piecewise max-pooling convolutional neural network. Second, we adopt a noise detection strategy, which is expected to dynamically detect and correct the original noisy label according to the similarity between sentence representation and entity-aware embeddings. Then, we aggregate the information from corpus and web tables to make the final relation prediction. Experimental results on a public benchmark dataset demonstrate that our proposed approach achieves significant improvements over the state-of-the-art baselines and can effectively reduce the noisy labeling problem.

Traditional Entity Linking is the task of linking name mentions in Web text with their referent entities in a knowledge base, and thus plays an important role in a range of Internet services, such as online recommender systems and Web search Engines. However, in our data integration framework, entity linking becomes the performance bottleneck. The reason is that data records of data integration systems are often short, noisy, informal texts with little context, and often contain phrases with ambiguous meanings. To rigorously address the entity linking problem for data integration, a novel graph-based short text entity linking framework is proposed. Firstly a hybrid candidate entity selection approach that considers both text description and instance data is introduced, then a graph-based semantic similarity metric combining context, topic and semantic correlation for short text entity disambiguation is proposed. Experimental results show good precision and recall of the proposed approaches.